{ "_meta": { "name": "AI video model specifications, with per-value provenance", "publisher": "RECATOOLS (RECASYS, Singapore)", "homepage": "https://recatools.com/datasets/ai-video-model-specs/", "format_version": "1", "schemas": [ "video/v1" ], "license": "CC-BY-4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/", "attribution": "RECATOOLS — https://recatools.com/datasets/ai-video-model-specs/", "as_of": "2026-08-20", "as_of_meaning": "The OLDEST verified_on in the dataset. A dataset is exactly as fresh as its stalest claim, so this is the date every value in it has been checked SINCE — not the date the files were generated.", "newest_verified_on": "2026-08-31", "counts": { "models": 17, "versions": 57, "constraints": 5, "values": 464 }, "states": { "known": 447, "unpublished": 17, "absent": 448 }, "states_meaning": { "known": "Read off a vendor page. Only this state carries a value.", "unpublished": "Someone checked, and the vendor publishes no figure. value is null, note says what was looked for, source_url is the page that was read. This is a finding, not a gap.", "absent": "Nobody has researched this field for this version. Do not read it as \"no\" or \"0\"." }, "sourcing_rule": "Primary vendor sources only — the vendor's own API reference, pricing page, model card, licence file or release post. No aggregators, no listicles. Where a marketing page and an API reference disagree, the API reference is the value and the marketing claim is recorded in `scope`. Where two vendor pages disagree and neither is authoritative, the value is null and the conflict is the note.", "field_dictionary": { "video/v1": { "max_duration_s": { "type": "int", "label": "Max clip length", "unit": "s", "help": "Longest single generation, in seconds. Not a stitched sequence." }, "min_duration_s": { "type": "int", "label": "Min clip length", "unit": "s" }, "duration_choices": { "type": "list", "label": "Selectable durations", "unit": "s", "help": "Only when the vendor offers a fixed set (6 or 10 and nothing between). Absent means free-form within the range." }, "max_resolution": { "type": "string", "label": "Max resolution", "help": "Of the BASE model. A paid upscale module belongs in scope, not here." }, "fps": { "type": "int", "label": "Frame rate", "unit": "fps" }, "native_audio": { "type": "bool", "label": "Native audio", "help": "The model itself emits synchronised audio — not a separate TTS pass bolted on after." }, "modes": { "type": "list", "label": "Generation modes", "help": "t2v text-to-video, i2v image-to-video, fl2v first/last frame, ref2v subject reference, s2v speech-driven, v2v video-to-video, ref2va reference to video+audio.", "vocabulary": [ "t2v", "i2v", "fl2v", "ref2v", "s2v", "v2v", "ref2va" ] }, "api_available": { "type": "bool", "label": "Public API", "help": "Self-serve. An enterprise contact form is not an API." }, "price": { "type": "money", "label": "Price", "help": "Vendor billing currency kept as billed — CNY stays CNY (entry standard, pricing section). The `per` member is load-bearing, not decoration: MiniMax H3 bills PER SECOND while its own 2.x line bills PER CLIP at fixed tiers, so a bare per-second number silently misstates half the family." }, "price_cn": { "type": "money", "label": "Price (mainland platform)", "help": "The SAME product sold on a separate mainland-China platform at a separately-set price — MiniMax's platform.minimax.io (USD) against platform.minimaxi.com (CNY), Zhipu's z.ai against bigmodel.cn. A second field rather than a converted figure, because these are two price lists, not one price in two currencies: there is no exchange rate that makes $0.13/s and ¥0.80/s the same number, and writing one implies a conversion the vendor never published." }, "open_weights": { "type": "bool", "label": "Open weights" }, "license": { "type": "string", "label": "Licence", "requires": "open_weights" }, "watermark": { "type": "enum", "label": "Watermark", "help": "An AIGC label is legally mandatory for CN-mainland services; say so in scope rather than reading it as a vendor choice.", "values": [ "always", "free-tier", "optional", "none" ] }, "region_availability": { "type": "string", "label": "Availability" }, "negative_prompt": { "type": "bool", "label": "Negative prompt", "help": "The VENDOR's own API. A wrapper service that pre-processes one does not count — that is the wrapper's feature." }, "max_input_images": { "type": "int", "label": "Max input images" } } } }, "models": [ { "slug": "google-veo", "name": "Google Veo", "category": "Video & Audio", "website_url": "https://deepmind.google/models/veo/", "entry_url": "https://recatools.com/ai-directory/google-veo/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "veo-3-1", "label": "Veo 3.1", "status": "preview", "released_at": null, "is_flagship": true, "fields": { "duration_choices": { "state": "known", "value": [ 4, 6, 8 ], "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "4K", "scope": "1080p and 4K are available ONLY on 8-second generations; 4- and 6-second clips are 720p. The headline 4K is real but conditional", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "always on — it cannot be disabled on the Gemini API", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": "fl2v is last-frame control, ref2v is image-based direction with up to 3 reference images, v2v is scene extension", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/video", "source_title": "Video generation in the Gemini API", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "two separate surfaces, Gemini API and Vertex AI. Every Veo 3.1 variant is still labelled Preview while Veo 3 and Veo 2 are 'Stable' AND simultaneously marked Deprecated — status wording and lifecycle stage point in opposite directions", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.4, "currency": "USD" }, "scope": "720p and 1080p; 4K is $0.60/s. Audio is included in the quoted price", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/pricing", "source_title": "Gemini Developer API Pricing", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "always", "scope": "SynthID, an INVISIBLE watermark applied unconditionally including on paid API output", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": "documented on VERTEX AI as an optional string; it does NOT appear in the Gemini API's Veo parameter table. Which surface you call decides whether you get it", "note": null, "source_url": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/video/generate-videos-from-text", "source_title": "Generate videos with Veo on Vertex AI from text prompts", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 3, "scope": "Veo 3.1 and 3.1 Fast only; 3.1 Lite, Veo 3 and Veo 2 are listed as N/A", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "price_cn", "open_weights", "license", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "veo-3-1-fast", "label": "Veo 3.1 Fast", "status": "preview", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 4, 6, 8 ], "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "4K", "scope": "same conditions as Veo 3.1 — 1080p and 4K on 8-second generations only", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "always on", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.1, "currency": "USD" }, "scope": "720p; rises to $0.30/s at 4K", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/pricing", "source_title": "Gemini Developer API Pricing", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "always", "scope": "SynthID", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 3, "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "modes", "api_available", "price_cn", "open_weights", "license", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "veo-3-1-lite", "label": "Veo 3.1 Lite", "status": "preview", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 4, 6, 8 ], "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "8-second generations only; no 4K on Lite, and no reference-image support at all", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "always on", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.05, "currency": "USD" }, "scope": "720p; $0.08/s at 1080p. Eight times cheaper than Veo 3.1 standard", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/pricing", "source_title": "Gemini Developer API Pricing", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "always", "scope": "SynthID", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "modes", "api_available", "price_cn", "open_weights", "license", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "veo-3", "label": "Veo 3", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 8, "scope": "fixed 8 seconds — no 4s or 6s option, unlike the 3.1 family", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "always on", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/veo", "source_title": "Generate videos with Veo 3.1 in Gemini API", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "marked Deprecated on the Gemini API pricing page but still served and priced", "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/pricing", "source_title": "Gemini Developer API Pricing", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.4, "currency": "USD" }, "scope": null, "note": null, "source_url": "https://ai.google.dev/gemini-api/docs/pricing", "source_title": "Gemini Developer API Pricing", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "modes", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "hailuo-video", "name": "Hailuo Video 海螺视频", "category": "Video & Audio", "website_url": "https://hailuoai.video", "entry_url": "https://recatools.com/ai-directory/hailuo-video/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "hailuo-h3", "label": "MiniMax H3 (Hailuo 3.0)", "status": "current", "released_at": "2026-07-31", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-v2-create.md", "source_title": "Create Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 4, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-v2-create.md", "source_title": "Create Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "2K", "scope": "directly selectable on the base create endpoint (resolution enum = 768P | 2K); a SEPARATE regeneration endpoint also upsells 768P→2K at its own price, but 2K is NOT gated behind it", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-v2-create.md", "source_title": "Create Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3", "source_title": "MiniMaxAI/MiniMax-H3 — Hugging Face (vendor model card)", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "32 kHz stereo, jointly generated with the video", "note": null, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3", "source_title": "MiniMaxAI/MiniMax-H3 — Hugging Face (vendor model card)", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "ref2va" ], "scope": "one create endpoint; mode is selected by content[].role (first_frame, last_frame, reference_image, reference_video, reference_audio). i2v/fl2v and ref2v are mutually exclusive in one request. Vendor names its two open checkpoints FL2VA and Ref2VA — the trailing 'A' means the output carries audio, so ref2va is the vendor's own framing of reference-to-video+audio", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-v2-create.md", "source_title": "Create Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/guides/video-generation", "source_title": "Video Generation — MiniMax API Docs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.13, "currency": "USD" }, "scope": "international platform (platform.minimax.io), 2K output. 768P output is $0.08/second. Mainland platform (platform.minimaxi.com) bills ¥0.80/s (2K) and ¥0.50/s (768P). Input material billed separately: first 5 reference images free then $0.04 each; reference video billed at output rate by its own duration; reference audio free. A separate /video-generation-v2-regeneration ENDPOINT re-emits an existing 768P H3 clip at 2K for $0.05/s (mainland CNY 0.30/s); it reuses the MiniMax-H3 model id, so it is an additional route and a billing row rather than a distinct model — and 2K is NOT gated behind it", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay as You Go — MiniMax API Docs", "verified_on": "2026-08-20" }, "price_cn": { "state": "known", "value": { "per": "second", "amount": 0.8, "currency": "CNY" }, "scope": "mainland platform platform.minimaxi.com, 2K output; 768P is CNY 0.50/s. The regeneration route is CNY 0.30/s. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay-as-you-go pricing — MiniMax platform", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": "open-sourced 2026-08-03, after the 2026-07-31 hosted launch; two checkpoints published (MiniMax-H3-Base-FL2VA, MiniMax-H3-Base-Ref2VA)", "note": null, "source_url": "https://www.minimax.io/news/minimax-h3-open-source", "source_title": "Open General Intelligence: MiniMax H3 Is Now Open Source — MiniMax News", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "MiniMax H3 Community License Agreement", "scope": "users in the USA, EU, UK and South Korea must submit an application form before use", "note": null, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3", "source_title": "MiniMaxAI/MiniMax-H3 — Hugging Face (vendor model card)", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "optional", "scope": "API: aigc_watermark boolean, optional, DEFAULT false — so API output is unwatermarked unless requested. Documented on the mainland create endpoint and on the international regeneration endpoint, but NOT listed on the international create endpoint. The consumer product (hailuoai.video) is separate and watermarks free-tier downloads", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-v2-regeneration.md", "source_title": "Create Video Regeneration Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "global", "scope": "two separate self-serve platforms with different billing currencies: platform.minimax.io (international, USD) and platform.minimaxi.com (mainland China, CNY). Open weights carry a licence application requirement for USA/EU/UK/South Korea", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay as You Go — MiniMax API Docs", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": "no negative_prompt field anywhere in the vendor create schema; top-level fields are exactly model, content, resolution, duration, ratio, callback_url (+ aigc_watermark). Wrapper services that expose one have added it themselves", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-v2-create.md", "source_title": "Create Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 9, "scope": "reference mode: ≤9 images, ≤3 video clips, ≤3 audio clips, ≤12 files total; per-asset caps video ≤50 MB, image ≤30 MB, audio ≤15 MB, request body ≤64 MB", "note": null, "source_url": "https://platform.minimax.io/docs/guides/video-generation.md", "source_title": "Video Generation — MiniMax API Docs", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "hailuo-2-3", "label": "MiniMax-Hailuo-2.3", "status": "legacy", "released_at": "2025-10-28", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": "768P only", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 6, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 6, 10 ], "scope": "10s is 768P-only; 1080P is 6s-only", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080P", "scope": "6-second clips only; 10-second clips top out at 768P (the default)", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "fps": { "state": "unpublished", "value": null, "scope": null, "note": "vendor does not publish an output frame rate for the 2.x line on either the t2v or i2v reference page", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "native_audio": { "state": "unpublished", "value": null, "scope": null, "note": "vendor documents no audio output for this line — the request schema has no audio field and the response is video only — but it is nowhere stated as absent, so recorded as unpublished rather than false", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "clip", "amount": 0.28, "currency": "USD" }, "scope": "international platform, 768P 6s. Also 768P 10s $0.56, 1080P 6s $0.49. Mainland: ¥2.00 / ¥4.00 / ¥3.50 per video respectively. Billed PER CLIP, not per second — unlike H3", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay as You Go — MiniMax API Docs", "verified_on": "2026-08-20" }, "price_cn": { "state": "known", "value": { "per": "clip", "amount": 2, "currency": "CNY" }, "scope": "mainland platform, 768P 6s; 768P 10s CNY 4.00, 1080P 6s CNY 3.50. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay-as-you-go pricing — MiniMax platform", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/guides/video-generation", "source_title": "Video Generation — MiniMax API Docs", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": "no negative_prompt field in the vendor t2v or i2v schema; only prompt (≤2000 chars) and prompt_optimizer", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" } }, "absent_fields": [ "license", "watermark", "region_availability", "max_input_images" ], "constraints": [ { "rule": "1080P is available on 6-second clips ONLY — choosing 10s forfeits 1080P and caps output at 768P", "affects": [ "duration_choices", "max_resolution" ], "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-video API reference — MiniMax platform", "verified_on": "2026-08-20" } ], "oldest_verified_on": "2026-08-20" }, { "id": "hailuo-2-3-fast", "label": "MiniMax-Hailuo-2.3-Fast", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 6, 10 ], "scope": "10s is 768P-only; 1080P is 6s-only", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080P", "scope": "6-second clips only", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "i2v" ], "scope": "listed in the i2v model enum only — it is absent from the t2v model enum, so this variant appears to be image-to-video only", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "clip", "amount": 0.19, "currency": "USD" }, "scope": "international platform, 768P 6s. Also 768P 10s $0.32, 1080P 6s $0.33. Mainland: ¥1.35 / ¥2.25 / ¥2.31 per video", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay as You Go — MiniMax API Docs", "verified_on": "2026-08-20" }, "price_cn": { "state": "known", "value": { "per": "clip", "amount": 1.35, "currency": "CNY" }, "scope": "mainland platform, 768P 6s; 768P 10s CNY 2.25, 1080P 6s CNY 2.31. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay-as-you-go pricing — MiniMax platform", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": "no negative_prompt field in the vendor i2v schema", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "fps", "native_audio", "open_weights", "license", "watermark", "region_availability", "max_input_images" ], "constraints": [ { "rule": "1080P is available on 6-second clips ONLY — choosing 10s forfeits 1080P and caps output at 768P", "affects": [ "duration_choices", "max_resolution" ], "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-video API reference — MiniMax platform", "verified_on": "2026-08-20" } ], "oldest_verified_on": "2026-08-20" }, { "id": "hailuo-02", "label": "MiniMax-Hailuo-02", "status": "legacy", "released_at": "2025-06-18", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 6, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 6, 10 ], "scope": "10s available at 512P and 768P; 1080P is 6s-only", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080P", "scope": "6-second clips only; this line uniquely also offers 512P", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "clip", "amount": 0.1, "currency": "USD" }, "scope": "international platform, 512P 6s (cheapest tier). Also 512P 10s $0.15, 768P 6s $0.28, 768P 10s $0.56, 1080P 6s $0.49. Mainland: ¥0.60 / ¥1.00 / ¥2.00 / ¥4.00 / ¥3.50 per video", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay as You Go — MiniMax API Docs", "verified_on": "2026-08-20" }, "price_cn": { "state": "known", "value": { "per": "clip", "amount": 0.6, "currency": "CNY" }, "scope": "mainland platform, 512P 6s; 512P 10s CNY 1.00, 768P 6s CNY 2.00, 768P 10s CNY 4.00, 1080P 6s CNY 3.50. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay-as-you-go pricing — MiniMax platform", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/guides/video-generation", "source_title": "Video Generation — MiniMax API Docs", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": "no negative_prompt field in the vendor t2v or i2v schema", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v.md", "source_title": "Text-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" } }, "absent_fields": [ "fps", "native_audio", "license", "watermark", "region_availability", "max_input_images" ], "constraints": [ { "rule": "1080P is available on 6-second clips ONLY; 10-second clips are limited to 512P or 768P", "affects": [ "duration_choices", "max_resolution" ], "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v", "source_title": "Image-to-video API reference — MiniMax platform", "verified_on": "2026-08-20" } ], "oldest_verified_on": "2026-08-20" }, { "id": "hailuo-01-line", "label": "T2V-01 / I2V-01 / S2V-01 (incl. -Director, -live)", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 6, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v.md", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 6 ], "scope": "6 seconds only; 10s not supported on this line", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v.md", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720P", "scope": "default and only value for this line", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v.md", "source_title": "Image-to-Video Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "ref2v" ], "scope": "split across three model IDs and endpoints: T2V-01/-Director (t2v), I2V-01/-Director/-live (i2v), S2V-01 (subject reference, character face only)", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-s2v.md", "source_title": "Subject Reference Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "still present in the model enums on the t2v/i2v/s2v reference pages, but ABSENT from the Pay-as-you-go price list entirely — no published price on either platform", "note": null, "source_url": "https://platform.minimax.io/docs/guides/pricing-paygo.md", "source_title": "Pay as You Go — MiniMax API Docs", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://platform.minimax.io/docs/guides/video-generation", "source_title": "Video Generation — MiniMax API Docs", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": "no negative_prompt field on any of the three endpoints", "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-s2v.md", "source_title": "Subject Reference Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 1, "scope": "S2V-01 only: subject_reference takes a single image (type 'character'); JPG/JPEG/PNG/WebP, <20 MB, shorter side >300px, aspect ratio 2:5 to 5:2", "note": null, "source_url": "https://platform.minimax.io/docs/api-reference/video-generation-s2v.md", "source_title": "Subject Reference Video Generation Task — MiniMax API Docs", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "fps", "native_audio", "price", "price_cn", "license", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "hunyuan-video", "name": "Hunyuan Video 混元视频", "category": "Video & Audio", "website_url": "https://hunyuan.tencent.com/modelSquare/home/list?modelCategory=VideoGeneration", "entry_url": "https://recatools.com/ai-directory/hunyuan-video/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "hunyuanvideo-1-5", "label": "HunyuanVideo 1.5", "status": "current", "released_at": "2025-11-20", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": "the README benchmarks 10-second 720p synthesis; the reference CLI's --video_length defaults to 121 frames (5s at 24fps) and takes a free-form frame count, so 10s is the longest length the vendor documents rather than a selectable preset", "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5", "source_title": "Tencent-Hunyuan/HunyuanVideo-1.5 — README", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "native checkpoints are 480p and 720p only; the 1080p figure people quote is a SEPARATE few-step super-resolution network applied afterwards, not a generation resolution", "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5", "source_title": "Tencent-Hunyuan/HunyuanVideo-1.5 — README", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5", "source_title": "Tencent-Hunyuan/HunyuanVideo-1.5 — README (diffusers usage)", "verified_on": "2026-08-20" }, "native_audio": { "state": "unpublished", "value": null, "scope": null, "note": "no audio component is documented in the repo or the model card; the card lists video output only", "source_url": "https://huggingface.co/tencent/HunyuanVideo-1.5", "source_title": "tencent/HunyuanVideo-1.5 — Hugging Face model card", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://huggingface.co/tencent/HunyuanVideo-1.5", "source_title": "tencent/HunyuanVideo-1.5 — Hugging Face model card", "verified_on": "2026-08-20" }, "api_available": { "state": "unpublished", "value": null, "scope": null, "note": "Tencent publishes no self-serve API tied to this checkpoint. Tencent Cloud sells a separate hosted 混元生视频 product, priced at 1.5 credits per 720p 5s call, but never states which model version backs it — so it cannot be attributed to HunyuanVideo 1.5", "source_url": "https://cloud.tencent.com/document/product/1616/118994", "source_title": "腾讯混元生视频 计费概述 — 腾讯云", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://huggingface.co/tencent/HunyuanVideo-1.5", "source_title": "tencent/HunyuanVideo-1.5 — Hugging Face model card", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "Tencent Hunyuan Community License", "scope": "the licence text opens by excluding the EU, UK and South Korea from its Territory — 'open weights' and 'usable in the EU' are different claims here", "note": null, "source_url": "https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanVideo-1.5/main/LICENSE", "source_title": "HunyuanVideo-1.5 LICENSE — Tencent Hunyuan Community License Agreement", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "global excl. EU/UK/KR", "scope": "licence-gated, not service-gated: the weights download anywhere, but the grant does not extend to those three territories", "note": null, "source_url": "https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanVideo-1.5/main/LICENSE", "source_title": "HunyuanVideo-1.5 LICENSE — Territory and licence grant", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": "in the reference inference script (--negative_prompt); Tencent ships no first-party hosted API for this checkpoint", "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5", "source_title": "Tencent-Hunyuan/HunyuanVideo-1.5 — README (inference parameters)", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "price", "price_cn", "watermark", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "hunyuanvideo-13b", "label": "HunyuanVideo (13B)", "status": "legacy", "released_at": "2024-12-03", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 5, "scope": "129 frames", "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo", "source_title": "Tencent-Hunyuan/HunyuanVideo — README", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "720x1280 / 1280x720 / 1104x832 / 832x1104 / 960x960; a 540p tier also exists", "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo", "source_title": "Tencent-Hunyuan/HunyuanVideo — README (supported resolutions)", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v" ], "scope": "the base 13B model is text-to-video; image-to-video ships as a separate checkpoint, HunyuanVideo-I2V. The 1.5 line lives in a SEPARATE repository, not a branch of this one", "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo", "source_title": "Tencent-Hunyuan/HunyuanVideo — README", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://github.com/Tencent-Hunyuan/HunyuanVideo", "source_title": "Tencent-Hunyuan/HunyuanVideo — README", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "Tencent Hunyuan Community License", "scope": "same EU/UK/South Korea territorial exclusion as 1.5", "note": null, "source_url": "https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanVideo-1.5/main/LICENSE", "source_title": "Tencent Hunyuan Community License Agreement", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "fps", "native_audio", "api_available", "price", "price_cn", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "jimeng-dreamina", "name": "Jimeng AI 即梦 (Dreamina)", "category": "Video & Audio", "website_url": "https://dreamina.capcut.com", "entry_url": "https://recatools.com/ai-directory/jimeng-dreamina/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "dreamina-app-seedance-2-5", "label": "Dreamina app — Seedance 2.5", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 30, "scope": "the app's standard mode, matching the API's single-generation cap. The page also advertises extension to 180 seconds in a beta long-video mode, which is stitching rather than one continuous generation", "note": null, "source_url": "https://dreamina.capcut.com/seedance/seedance-2-5", "source_title": "Free Seedance 2.5 AI Video Generator with Audio — Dreamina", "verified_on": "2026-08-20" }, "max_resolution": { "state": "unpublished", "value": null, "scope": null, "note": "unresolved between two vendor pages: the Dreamina product page claims 4K, while the ModelArk API caps dreamina-seedance-2-5 at 1080p and exposes 4k only on Seedance 2.0. Both are ByteDance's own surfaces, so the conflict IS the finding — recorded as unknown rather than picking a side", "source_url": "https://dreamina.capcut.com/seedance/seedance-2-5", "source_title": "Free Seedance 2.5 AI Video Generator with Audio — Dreamina", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://dreamina.capcut.com/seedance/seedance-2-5", "source_title": "Free Seedance 2.5 AI Video Generator with Audio — Dreamina", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "ref2v", "s2v" ], "scope": "the app accepts text prompts, scripts, reference photos, videos, music and style guides, plus a green-screen reference workflow", "note": null, "source_url": "https://dreamina.capcut.com/seedance/seedance-2-5", "source_title": "Free Seedance 2.5 AI Video Generator with Audio — Dreamina", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": false, "scope": "Dreamina is a credit-billed consumer app and publishes no API of its own. The same models are exposed programmatically through BytePlus ModelArk — see the `seedance` entry", "note": null, "source_url": "https://dreamina.capcut.com/tools/ai-video-generator", "source_title": "AI Video Generator: Seedance, Sora, Veo and More — Dreamina", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "free-tier", "scope": "watermark-free download is a paid upgrade", "note": null, "source_url": "https://dreamina.capcut.com/seedance/seedance-2-5", "source_title": "Free Seedance 2.5 AI Video Generator with Audio — Dreamina", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "global", "scope": "Dreamina is the international front door; 即梦 at jimeng.jianying.com is the mainland-China one, with separate accounts", "note": null, "source_url": "https://dreamina.capcut.com/tools/ai-video-generator", "source_title": "AI Video Generator: Seedance, Sora, Veo and More — Dreamina", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "fps", "price", "price_cn", "open_weights", "license", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "dreamina-app-seedance-2-0", "label": "Dreamina app — Seedance 2.0", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_resolution": { "state": "known", "value": "4K", "scope": "unlike the 2.5 claim, this one IS corroborated by the API, where dreamina-seedance-2-0 accepts resolution=4k", "note": null, "source_url": "https://dreamina.capcut.com/tools/seedance-2-0", "source_title": "Official Seedance 2.0: Your Multimodal 4K Video Generator — Dreamina", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "synchronises narration, dialogue, sound effects and visuals", "note": null, "source_url": "https://dreamina.capcut.com/tools/seedance-2-0", "source_title": "Official Seedance 2.0: Your Multimodal 4K Video Generator — Dreamina", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "ref2v", "s2v" ], "scope": null, "note": null, "source_url": "https://dreamina.capcut.com/tools/seedance-2-0", "source_title": "Official Seedance 2.0: Your Multimodal 4K Video Generator — Dreamina", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://dreamina.capcut.com/tools/ai-video-generator", "source_title": "AI Video Generator: Seedance, Sora, Veo and More — Dreamina", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "free-tier", "scope": null, "note": null, "source_url": "https://dreamina.capcut.com/tools/seedance-2-0", "source_title": "Official Seedance 2.0: Your Multimodal 4K Video Generator — Dreamina", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 9, "scope": "up to 12 reference resources — 9 photos, 3 videos, 3 audio clips — exactly matching the ModelArk limits for the 2.0 series", "note": null, "source_url": "https://dreamina.capcut.com/tools/seedance-2-0", "source_title": "Official Seedance 2.0: Your Multimodal 4K Video Generator — Dreamina", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "duration_choices", "fps", "price", "price_cn", "open_weights", "license", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "jimeng-app-cn", "label": "即梦 Jimeng (mainland China app)", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "unpublished", "value": null, "scope": null, "note": "the Jimeng and Dreamina generator UIs are behind a login wall and neither product publishes a specification page or help-centre article with the in-app duration picker; the model-level limits live on the `seedance` entry instead", "source_url": "https://jimeng.jianying.com/", "source_title": "即梦AI — 一站式AI创作平台", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "ref2v", "s2v" ], "scope": "the widget labels the mode 全能参考; 数字人 and 动作模仿 are separate tools", "note": null, "source_url": "https://jimeng.jianying.com/", "source_title": "即梦AI — 一站式AI创作平台", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": false, "scope": "consumer app; the mainland programmatic route is Volcano Engine 火山引擎, a separate product", "note": null, "source_url": "https://jimeng.jianying.com/", "source_title": "即梦AI — 一站式AI创作平台", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "CN mainland", "scope": null, "note": null, "source_url": "https://jimeng.jianying.com/", "source_title": "即梦AI — 一站式AI创作平台", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 9, "scope": "the generator widget states 上传最多12个参考素材 across 图/文/音/视频 — the same 12-slot budget Dreamina breaks down as 9 photos, 3 videos, 3 audio", "note": null, "source_url": "https://jimeng.jianying.com/", "source_title": "即梦AI — 一站式AI创作平台", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "max_resolution", "fps", "native_audio", "price", "price_cn", "open_weights", "license", "watermark", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "kling", "name": "Kling", "category": "Video & Audio", "website_url": "https://klingai.com", "entry_url": "https://recatools.com/ai-directory/kling/", "schema": "video/v1", "oldest_verified_on": "2026-08-21", "versions": [ { "id": "kling-3-0", "label": "Kling 3.0", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 3, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "4K", "scope": "resolution enum 720p | 1080p | 4k; 4K bills at $0.42/s against $0.084/s at 720p", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "fps": { "state": "unpublished", "value": null, "scope": null, "note": "Kling publishes no frame rate — its own Video Capability Map lists duration and resolution and no fps, and no endpoint takes an fps parameter", "source_url": "https://kling.ai/document-api/guides/capability-map/video.md", "source_title": "Video Capability Map — Kling AI API Documentation", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "opt-in: settings.audio enum native | off, default off", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v" ], "scope": "ref2v runs through the Element library rather than raw reference images", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.084, "currency": "USD" }, "scope": "720p without native audio. 1080p $0.112/s, 4K $0.42/s; with native audio 720p $0.126/s, 1080p $0.168/s. Billed in Units, 1 Unit = $0.14", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": "options.watermark_info.enabled defaults false; when true a watermarked copy is returned alongside the clean one", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "region_availability": { "state": "known", "value": "global, single Singapore API endpoint", "scope": "api-singapore.klingai.com is the only regional endpoint documented on the international open platform", "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": "the current endpoint has no negative_prompt field — positive and negative descriptions both go in the prompt. The superseded legacy endpoint did expose one", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 2, "scope": "first_frame + last_frame; last-frame-only is not supported. Up to 3 Elements may additionally be referenced", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "kling-3-0-omni", "label": "Kling 3.0 Omni", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 3, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "4K", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/capability-map/video.md", "source_title": "Video Capability Map — Kling AI API Documentation", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "settings.audio enum native | off, default off", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": "video reference and multi-image to video are marked supported on Omni and O1 only", "note": null, "source_url": "https://kling.ai/document-api/guides/capability-map/video.md", "source_title": "Video Capability Map — Kling AI API Documentation", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.084, "currency": "USD" }, "scope": "720p, no video input, no native audio. With native audio 720p $0.112/s, 1080p $0.14/s; with video input 720p $0.126/s, 1080p $0.168/s; 4K $0.42/s throughout", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-omni/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (3.0 / 3.0 Omni)", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "fps", "price_cn", "open_weights", "license", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "kling-3-0-turbo", "label": "Kling 3.0 Turbo", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-turbo/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 Turbo)", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 3, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-turbo/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 Turbo)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "enum is 720p | 1080p only — no 4K on Turbo, unlike Kling 3.0", "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-turbo/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 Turbo)", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "always on — the endpoint exposes no audio toggle and the price list carries only a 'with native audio' row", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": "the capability map shows no first/last frame and no Element control for Turbo", "note": null, "source_url": "https://kling.ai/document-api/guides/capability-map/video.md", "source_title": "Video Capability Map — Kling AI API Documentation", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.112, "currency": "USD" }, "scope": "720p with native audio (0.8 Units/s); 1080p $0.14/s", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-turbo/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 Turbo)", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/3-0-turbo/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (3.0 Turbo)", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "fps", "price_cn", "open_weights", "license", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "kling-o1", "label": "Kling O1", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 3, "scope": "integers 3-10; with only a first frame and no other reference, only 5 or 10 are accepted", "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": false, "scope": "the audio enum is original | off — 'original' RETAINS an input video's sound; the model synthesises none, and the price list has no audio dimension for O1", "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": "content types: prompt, first_frame, last_frame, refer_image, feature_video, base_video, element", "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.084, "currency": "USD" }, "scope": "720p, no video input; 1080p $0.112/s. With video input 720p $0.126/s, 1080p $0.168/s", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/o1/video-omni.md", "source_title": "Video Generation — Kling AI API Documentation (O1)", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "fps", "price_cn", "open_weights", "license", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "kling-2-6", "label": "Kling 2.6", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" }, "duration_choices": { "state": "known", "value": [ 5, 10 ], "scope": "the API duration enum is exactly {5, 10} on both t2v and i2v. Kling's own Video Capability Map advertises 3~10s for this model; that range is NOT reachable through the documented API", "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "audio=native FORCES 1080p — no 720p rate exists for the audio tiers", "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "s2v" ], "scope": "s2v is voice-reference input (at most 2 voices) and requires audio != off; first+last frame requires 1080p", "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.042, "currency": "USD" }, "scope": "720p silent; 1080p silent $0.07/s; with native audio (1080p only) $0.14/s; with voice control $0.168/s", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-6/text-to-video.md", "source_title": "Text to Video — Kling AI API Documentation (2.6)", "verified_on": "2026-08-21" } }, "absent_fields": [ "min_duration_s", "fps", "price_cn", "open_weights", "license", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "kling-2-5-turbo", "label": "Kling 2.5 Turbo", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-5-turbo/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (2.5 Turbo)", "verified_on": "2026-08-21" }, "duration_choices": { "state": "known", "value": [ 5, 10 ], "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-5-turbo/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (2.5 Turbo)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-5-turbo/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (2.5 Turbo)", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": false, "scope": "no audio parameter on this endpoint; the price list carries only a 'no native audio' row", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v" ], "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/capability-map/video.md", "source_title": "Video Capability Map — Kling AI API Documentation", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://kling.ai/document-api/guides/get-started/quick-start.md", "source_title": "Quick Start — Kling AI API Documentation", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.042, "currency": "USD" }, "scope": "720p; 1080p $0.07/s", "note": null, "source_url": "https://kling.ai/document-api/pricing/base/video.md", "source_title": "Video — Kling AI API Documentation (Basic APIs Pricing)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": null, "note": null, "source_url": "https://kling.ai/document-api/api/video/2-5-turbo/image-to-video.md", "source_title": "Image to Video — Kling AI API Documentation (2.5 Turbo)", "verified_on": "2026-08-21" } }, "absent_fields": [ "min_duration_s", "fps", "price_cn", "open_weights", "license", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" } ] }, { "slug": "ltx-studio", "name": "LTX Studio", "category": "Video & Audio", "website_url": "https://ltx.studio", "entry_url": "https://recatools.com/ai-directory/ltx-studio/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "ltx-2-5", "label": "LTX-2.5", "status": "current", "released_at": "2026-08-11", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 20, "scope": "ltx-2-5-FAST at 720p or 1080p and 24/25 fps only. Every other combination caps at 10s, and ltx-2-5-PRO caps at 10s everywhere", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-5", "source_title": "LTX-2.5 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 6, "scope": null, "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-5", "source_title": "LTX-2.5 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 6, 8, 10, 12, 14, 16, 18, 20 ], "scope": "the full ladder exists only on ltx-2-5-fast at 720p/1080p and 24/25 fps; at 48/50 fps, at 1440p/4K, and on pro, the choices are [6, 8, 10]. Passing duration:null lets the model choose from the prompt", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-5", "source_title": "LTX-2.5 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "4K", "scope": "ltx-2-5-FAST only. ltx-2-5-PRO tops out at 1080p — ltx.io's marketing tier block claims Pro reaches 1440p and 4K and the API docs contradict it. Docs win", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-5", "source_title": "LTX-2.5 — LTX Documentation (support matrix, resolutions)", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 50, "scope": "24, 25, 48, 50 on fast; 24, 25, 50 on pro. Default 24. Choosing 48 or 50 cuts max duration to 10s", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-5", "source_title": "LTX-2.5 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "generate_audio defaults TRUE — the only model in this set that emits synchronised audio by default rather than on request", "note": null, "source_url": "https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-text-to-video", "source_title": "Generate video from text — LTX API Reference", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "s2v" ], "scope": "fl2v via last_frame_uri; s2v is the audio-to-video endpoint, where output length follows the input audio. Retake, extend and reframe are NOT on 2.5 — they need ltx-2-3-pro", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-5", "source_title": "LTX-2.5 — LTX Documentation (supported endpoints)", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.ltx.io/models", "source_title": "Supported Models — LTX Documentation", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.09, "currency": "USD" }, "scope": "ltx-2-5-fast at 720p. Fast: $0.09 / $0.13 / $0.19 / $0.30 per second at 720p / 1080p / 1440p / 4K. Pro: $0.12 at 720p, $0.17 at 1080p", "note": null, "source_url": "https://docs.ltx.io/pricing", "source_title": "Pricing — LTX Documentation", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": "22B dev and distilled checkpoints on Hugging Face. The hosted fast/pro tiers are NOT the same artefacts — the downloadable model's own examples run 121 frames at 24fps (about 5s) at 960x544, nothing like the API's 4K/50fps/20s envelope", "note": null, "source_url": "https://huggingface.co/Lightricks/LTX-2.5", "source_title": "Lightricks/LTX-2.5 — Hugging Face model card", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "LTX-2.x Community License", "scope": "free below $10M annual revenue, paid Commercial Use Agreement above; transferring fine-tunes may require a paid licence", "note": null, "source_url": "https://huggingface.co/Lightricks/LTX-2.5", "source_title": "Lightricks/LTX-2.5 — Hugging Face model card", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": "read against the complete documented request body: prompt, model, duration, resolution, fps, generate_audio, camera_motion, last_frame_uri", "note": null, "source_url": "https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-text-to-video", "source_title": "Generate video from text — LTX API Reference", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 2, "scope": "image_uri (first frame) plus optional last_frame_uri; a last frame cannot be combined with automatic duration", "note": null, "source_url": "https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-image-to-video", "source_title": "Generate video from image — LTX API Reference", "verified_on": "2026-08-20" } }, "absent_fields": [ "price_cn", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "ltx-2-3", "label": "LTX-2.3", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 20, "scope": "ltx-2-3-fast at 720p/1080p and 24/25 fps only; pro caps at 10s at every resolution", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-3", "source_title": "LTX-2.3 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 6, 8, 10, 12, 14, 16, 18, 20 ], "scope": "fast at 720p/1080p and 24-25fps only; everything else is [6, 8, 10]", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-3", "source_title": "LTX-2.3 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "4K", "scope": "both fast and pro reach 4K on 2.3 — unlike 2.5, where pro stops at 1080p", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-3", "source_title": "LTX-2.3 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 50, "scope": "24, 25, 48, 50 on both variants", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-3", "source_title": "LTX-2.3 — LTX Documentation (support matrix)", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-text-to-video", "source_title": "Generate video from text — LTX API Reference (generate_audio default true)", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "s2v", "v2v" ], "scope": "audio-to-video, retake, extend and reframe require ltx-2-3-pro — these editing modes exist ONLY on 2.3 and are absent from the newer 2.5", "note": null, "source_url": "https://docs.ltx.io/models/ltx-2-3", "source_title": "LTX-2.3 — LTX Documentation (supported endpoints)", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.ltx.io/models", "source_title": "Supported Models — LTX Documentation", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.03, "currency": "USD" }, "scope": "ltx-2-3-fast at 720p. Fast: $0.03 / $0.06 / $0.12 / $0.24 at 720p / 1080p / 1440p / 4K. Pro: $0.04 / $0.08 / $0.16 / $0.32", "note": null, "source_url": "https://docs.ltx.io/pricing", "source_title": "Pricing — LTX Documentation", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "ltx-2", "label": "LTX-2", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "native_audio": { "state": "known", "value": true, "scope": "joint audio-video generation with bidirectional cross-attention, per the technical report summary", "note": null, "source_url": "https://ltx.io/model/ltx-2", "source_title": "LTX-2 Model — LTX (technical report)", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": false, "scope": "the API model enum is ltx-2-3-fast, ltx-2-3-pro, ltx-2-5-fast, ltx-2-5-pro — LTX-2 is no longer callable, though the vendor still documents it and its weights remain downloadable", "note": null, "source_url": "https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-text-to-video", "source_title": "Generate video from text — LTX API Reference (model enum)", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://ltx.io/model/ltx-2", "source_title": "LTX-2 Model — LTX", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "duration_choices", "max_resolution", "fps", "modes", "price", "price_cn", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "luma-ai", "name": "Luma AI", "category": "Video & Audio", "website_url": "https://lumalabs.ai", "entry_url": "https://recatools.com/ai-directory/luma-ai/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "ray-3-2", "label": "Ray3.2", "status": "current", "released_at": "2026-06-09", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 20, "scope": "20s applies to video-to-video at 1080p, not to a single text- or image-to-video generation, which caps at 10s", "note": null, "source_url": "https://lumalabs.ai/api", "source_title": "Build with Luma APIs", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 5, 10 ], "scope": "text-to-video and image-to-video. Video-to-video (Modify Video V2) supports 10, 15 or 20s, and extensions bill in 5-second blocks", "note": null, "source_url": "https://docs.agents.lumalabs.ai/guides/model/index.md", "source_title": "Luma Agents API — Models", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "540p, 720p and 1080p, plus a 360p draft tier. Ray3.2's genuinely distinctive spec is not resolution but native HDR in 16-bit colour with EXR export for compositing — nothing else in this set offers it", "note": null, "source_url": "https://docs.agents.lumalabs.ai/guides/model/index.md", "source_title": "Luma Agents API — Models", "verified_on": "2026-08-20" }, "native_audio": { "state": "unpublished", "value": null, "scope": null, "note": "Luma documents no native audio generation for Ray3.2. Audio is handled by separate ElevenLabs integrations and, on the older Dream Machine API, by a distinct add-audio endpoint", "source_url": "https://docs.agents.lumalabs.ai/guides/model/index.md", "source_title": "Luma Agents API — Models", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "v2v", "fl2v" ], "scope": "fl2v via multi-keyframe. Reframe (aspect-ratio conversion) and extension are additional modes that do not map onto the shared vocabulary", "note": null, "source_url": "https://docs.agents.lumalabs.ai/guides/model/index.md", "source_title": "Luma Agents API — Models", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "new as of Ray3.2 — for the first time the model is available as an API. Two tiers: Build (usage-based) and Scale (dedicated capacity)", "note": null, "source_url": "https://lumalabs.ai/news/introducing-ray-3-2", "source_title": "Luma Introduces Ray3.2 Model and API", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "clip", "amount": 1.2, "currency": "USD" }, "scope": "per 5-second 1080p SDR block ($3.60 for 10s). Other tiers per 5s: 720p $0.30, 540p $0.15, 360p draft $0.06. HDR costs 2x, HDR+EXR 3x. The 1080p tier costs 4x the 720p tier — a much steeper resolution premium than any other vendor here", "note": null, "source_url": "https://docs.agents.lumalabs.ai/guides/pricing/index.md", "source_title": "Luma Agents API — Pricing", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 64, "scope": "up to 64 anchors per the developer docs. Luma's own launch post and API landing page both say 16 — the marketing figure and the API figure disagree, and 64 is the one in the docs", "note": null, "source_url": "https://docs.agents.lumalabs.ai/guides/model/index.md", "source_title": "Luma Agents API — Models", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "fps", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [ { "rule": "20s applies to video-to-video (Modify Video V2) at 1080p, which offers 10, 15 or 20s. A single text-to-video or image-to-video generation caps at 10s and offers 5 or 10 — so the 20s maximum is not reachable from the listed duration choices.", "affects": [ "max_duration_s", "duration_choices" ], "source_url": "https://docs.agents.lumalabs.ai/guides/model/index.md", "source_title": "Luma model guide — durations by generation mode", "verified_on": "2026-08-20" } ], "oldest_verified_on": "2026-08-20" }, { "id": "ray-2", "label": "Ray 2 / Ray 2 Flash (Dream Machine API)", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_resolution": { "state": "known", "value": "4K", "scope": "as written in the Dream Machine API docs (540p, 720p, 1080, 4k). ⚠️ Luma's own AI-assistant page says explicitly not to conflate Dream Machine and Ray2 with the current model — the old docs still advertise 4K, which the current ray-3.2 does NOT offer, so a table that reads docs.lumalabs.ai will report a 4K Luma model that no longer exists", "note": null, "source_url": "https://docs.lumalabs.ai/docs/video-generation", "source_title": "Luma Dream Machine API — Video Generation", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v" ], "scope": "keyframe modes cover image inputs, generation references and looping", "note": null, "source_url": "https://docs.lumalabs.ai/docs/video-generation", "source_title": "Luma Dream Machine API — Video Generation", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "the Dream Machine API and its docs are still live, but Luma states Dream Machine and Ray2 are deprecated", "note": null, "source_url": "https://lumalabs.ai/llm-info", "source_title": "Luma — Official Information for AI Assistants", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "duration_choices", "fps", "native_audio", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "moonvalley-marey", "name": "Moonvalley (Marey)", "category": "Video & Audio", "website_url": "https://moonvalley.com", "entry_url": "https://recatools.com/ai-directory/moonvalley-marey/", "schema": "video/v1", "oldest_verified_on": "2026-08-31", "versions": [ { "id": "marey", "label": "Marey", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "unpublished", "value": null, "scope": null, "note": "No duration is published. The \"shot extension\" feature explicitly extends clip length — \"each additional second flows organically from your original footage\" — without stating any starting length or ceiling.", "source_url": "https://moonvalley.com/marey", "source_title": "Marey — Moonvalley", "verified_on": "2026-08-31" }, "max_resolution": { "state": "unpublished", "value": null, "scope": null, "note": "Moonvalley publishes no resolution anywhere on its own site. The page claims \"high-resolution cinematic footage\" as training data and \"no upscaling\" in output, neither of which is an output specification.", "source_url": "https://moonvalley.com/marey", "source_title": "Marey — Moonvalley", "verified_on": "2026-08-31" }, "fps": { "state": "unpublished", "value": null, "scope": null, "note": "No frame rate is published.", "source_url": "https://moonvalley.com/marey", "source_title": "Marey — Moonvalley", "verified_on": "2026-08-31" }, "native_audio": { "state": "unpublished", "value": null, "scope": null, "note": "Audio is not mentioned on the model page in any form.", "source_url": "https://moonvalley.com/marey", "source_title": "Marey — Moonvalley", "verified_on": "2026-08-31" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": "Stated plainly: \"Marey generates image-to-video and text-to-video\". The page also describes camera control, motion transfer, trajectory control, keyframing, pose control and shot extension as directorial features — none of which is a generation mode in this vocabulary, so none is recorded here.", "note": null, "source_url": "https://moonvalley.com/marey", "source_title": "Marey — Moonvalley", "verified_on": "2026-08-31" }, "api_available": { "state": "known", "value": false, "scope": "Moonvalley runs a \"PUBLIC API waitlist\" and says its public APIs will be available \"soon\". Marey IS reachable programmatically today, but only through third parties the vendor points to — ComfyUI native API nodes and fal.ai — which is a reseller route, not a first-party API.", "note": null, "source_url": "https://moonvalley.com/api", "source_title": "Inference / API — Moonvalley", "verified_on": "2026-08-31" } }, "absent_fields": [ "min_duration_s", "duration_choices", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-31" } ] }, { "slug": "pika-labs", "name": "Pika Labs", "category": "Video & Audio", "website_url": "https://pika.art", "entry_url": "https://recatools.com/ai-directory/pika-labs/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "pika-2-5", "label": "Pika 2.5", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": "image-to-video only; text-to-video caps at 5", "note": null, "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 5, 10 ], "scope": "image-to-video: 5 or 10, default 5. TEXT-to-video is fixed at 5 seconds — the two modes of the same model differ", "note": null, "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "720p or 1080p, default 1080p", "note": null, "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" }, "native_audio": { "state": "unpublished", "value": null, "scope": null, "note": "no audio parameter in the Pika 2.5 request schema. Pika ships audio as separate models (Music, SFX, Speech, Soundtrack) rather than as synchronised output from the video model", "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://dev.pika.art/llms.txt", "source_title": "Pika API — model and operation index (llms.txt)", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": "First-party self-serve API at dev.pika.art: own account, own key (X-API-Key or Bearer), own billing, base URL api.dev.pika.art. Access is membership-gated — llms.txt sends you to \"manage membership\" and the job envelope has a membership_required error code. RATE LIMITS EXIST BUT NO FIGURE IS PUBLISHED: a 429 is documented as \"rate or concurrency limit reached\", spanning requests per minute, requests per day and concurrent jobs, per org, with Retry-After. ⚠️ The catalogue is mostly NOT Pika: 107 operations across 13 vendor namespaces, of which only the 11 under pika/ are Pika's own — the rest are ByteDance, Google, Kling, MiniMax, OpenAI, xAI and others. Listicles routinely attribute Seedance's 4K and 30-second specs to Pika because both sit in the same catalogue.", "note": null, "source_url": "https://dev.pika.art/llms.txt", "source_title": "Pika API — llms.txt (catalogue, auth, error semantics)", "verified_on": "2026-08-22" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.04, "currency": "USD" }, "scope": "720p; 1080p is $0.06/s. Only successful generations are charged", "note": null, "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": "a first-party negative_prompt string on Pika's own API; a seed parameter is also exposed", "note": null, "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 1, "scope": "the image parameter takes a single URL", "note": null, "source_url": "https://dev.pika.art/llms/pika/pika-2.5/image-to-video", "source_title": "Pika API — Pika 2.5 Image to Video", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "fps", "price_cn", "open_weights", "license", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "pika-2-5-keyframe", "label": "Pika 2.5 Keyframe (Pikaframes)", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_resolution": { "state": "known", "value": "1080p", "scope": "720p or 1080p, default 1080p", "note": null, "source_url": "https://dev.pika.art/llms/pika/pikaframes/image-to-video", "source_title": "Pika API — Pika 2.5 Keyframe, Image to Video", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "fl2v" ], "scope": "consecutive pairs of the supplied keyframes become transitions, generalising first/last-frame beyond two frames", "note": null, "source_url": "https://dev.pika.art/llms/pika/pikaframes/image-to-video", "source_title": "Pika API — Pika 2.5 Keyframe, Image to Video", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.04, "currency": "USD" }, "scope": "720p; $0.06/s at 1080p", "note": null, "source_url": "https://dev.pika.art/llms/pika/pikaframes/image-to-video", "source_title": "Pika API — Pika 2.5 Keyframe, Image to Video", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://dev.pika.art/llms/pika/pikaframes/image-to-video", "source_title": "Pika API — Pika 2.5 Keyframe, Image to Video", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 5, "scope": "2-5 ordered keyframe image URLs; durations over 5 seconds require exactly 2 keyframes", "note": null, "source_url": "https://dev.pika.art/llms/pika/pikaframes/image-to-video", "source_title": "Pika API — Pika 2.5 Keyframe, Image to Video", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "duration_choices", "fps", "native_audio", "api_available", "price_cn", "open_weights", "license", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "pixverse", "name": "PixVerse", "category": "Video & Audio", "website_url": "https://pixverse.ai", "entry_url": "https://recatools.com/ai-directory/pixverse/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "c1", "label": "PixVerse C1", "status": "current", "released_at": "2026-04-07", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 1, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "quality enum 360p, 540p, 720p, 1080p", "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "fps": { "state": "unpublished", "value": null, "scope": null, "note": "PixVerse exposes no fps parameter and publishes no output frame rate anywhere in the platform docs — duration, quality and aspect_ratio are the only output controls", "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs (full parameter list)", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "opt-in via generate_audio_switch, default FALSE, and it raises the credit rate (1080p goes 19 to 24 credits/s). 'Has native audio' is true; 'generates audio by default' is not", "note": null, "source_url": "https://docs.platform.pixverse.ai/model-pricing-796039m0", "source_title": "Model and Pricing — PixVerse Platform Docs (C1)", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v" ], "scope": "the vendor names them Text-to-video, Image-to-video, Transition and Fusion", "note": null, "source_url": "https://docs.platform.pixverse.ai/model-pricing-796039m0", "source_title": "Model and Pricing — PixVerse Platform Docs (C1)", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/how-does-the-api-work-882967m0", "source_title": "How does the API work? — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "credit", "amount": 0.01, "currency": "USD" }, "scope": "$10 = 1,000 credits at the smallest pack. C1 bills per second: 360p 6 cr/s, 540p 8, 720p 10, 1080p 19 silent; 8/10/13/24 with audio. A 5s 1080p clip with audio is 120 credits, about $1.20", "note": null, "source_url": "https://docs.platform.pixverse.ai/pricing-796039m0", "source_title": "Pricing — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "optional", "scope": "the API exposes a water_mark boolean. The consumer free-tier watermark is widely reported by third parties but appears on no PixVerse-owned page, so only the API parameter is recorded", "note": null, "source_url": "https://docs.platform.pixverse.ai/how-does-the-api-work-882967m0", "source_title": "How does the API work? — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "global", "scope": "the vendor states the platform serves creators across 175 countries; no per-region model gating is documented", "note": null, "source_url": "https://pixverse.ai/en/blog/pixverse-introduces-c1-ai-video-model-for-film-production", "source_title": "PixVerse Introduces C1, an AI Video Model Built for Film Production", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-882970m0", "source_title": "Text-to-video — PixVerse Platform Docs", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "v6", "label": "PixVerse V6", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/v6-2056814m0", "source_title": "V6 — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 1, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/v6-2056814m0", "source_title": "V6 — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/v6-2056814m0", "source_title": "V6 — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "switchable across all five modes; generate_audio_switch defaults false", "note": null, "source_url": "https://docs.platform.pixverse.ai/v6-2056814m0", "source_title": "V6 — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "v2v", "ref2v" ], "scope": "vendor names: Text-to-Video, Image-to-Video, Transition, Video Extension, Reference-to-Video. Multi-clip is available on t2v and i2v only", "note": null, "source_url": "https://docs.platform.pixverse.ai/v6-2056814m0", "source_title": "V6 — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs (model enum)", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "credit", "amount": 0.01, "currency": "USD" }, "scope": "V6 is 5/7/9/18 credits per second at 360p/540p/720p/1080p silent, 7/9/12/23 with audio; Fusion with VIDEO references costs double", "note": null, "source_url": "https://docs.platform.pixverse.ai/model-pricing-796039m0", "source_title": "Model and Pricing — PixVerse Platform Docs (V6)", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "fps", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "v5-6", "label": "PixVerse V5.6", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": "720p and below; 1080p caps at 8s", "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 5, 8, 10 ], "scope": "1080p cannot use 10s on v5.5/v5.6", "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs (duration per model)", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://docs.platform.pixverse.ai/model-pricing-796039m0", "source_title": "Model and Pricing — PixVerse Platform Docs (V5.6)", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "generate_audio_switch exists on v5.5, v5.6, v6 and c1 only — NOT on v5 and earlier", "note": null, "source_url": "https://docs.platform.pixverse.ai/text-to-video-generation-13016634e0", "source_title": "Text-to-Video generation — PixVerse Platform Docs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "credit", "amount": 0.01, "currency": "USD" }, "scope": "V5.6 bills per CLIP, not per second — 5s costs 35/35/45/75 credits at 360p/540p/720p/1080p silent; 10s costs 77/77/99 with no 1080p. The billing MODEL changes at v6, which is what a flat duration column destroys", "note": null, "source_url": "https://docs.platform.pixverse.ai/model-pricing-796039m0", "source_title": "Model and Pricing — PixVerse Platform Docs (V5.6)", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "fps", "modes", "api_available", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "runway", "name": "Runway", "category": "Video & Audio", "website_url": "https://runwayml.com", "entry_url": "https://recatools.com/ai-directory/runway/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "gen4-5", "label": "Gen-4.5", "status": "current", "released_at": "2025-12-01", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": "an integer from 2 to 10, per single generation", "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 2, "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "the API expresses output size as `ratio`, whose allowed values are 1280:720, 720:1280, 1104:832, 960:960, 832:1104, 1584:672. There is no 1080p or 4K option on gen4.5 — Runway sells a separate upscaler model for that", "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "documented for the MODEL in Runway's research post, and NOT exposed by the API: the gen4.5 request schema lists only promptText, promptImage, ratio, duration, seed, contentModeration, outputFormat, proresProfile, and gen4.5 bills a flat 12 credits/s — unlike veo3.1 on the same API, which is priced separately with and without audio", "note": null, "source_url": "https://runway.com/research/introducing-runway-gen-4.5", "source_title": "Runway Research — Introducing Runway Gen-4.5", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/guides/models.md", "source_title": "Runway API — Models", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "self-serve via the Runway Dev portal; credits sold at $0.01 each", "note": null, "source_url": "https://docs.dev.runwayml.com/guides/pricing.md", "source_title": "Runway API — Pricing and Costs", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.12, "currency": "USD" }, "scope": "12 credits per second of output at $0.01/credit, minimum 1 credit per generation", "note": null, "source_url": "https://docs.dev.runwayml.com/guides/pricing.md", "source_title": "Runway API — Pricing and Costs", "verified_on": "2026-08-20" }, "watermark": { "state": "unpublished", "value": null, "scope": null, "note": "Runway publishes no watermark policy for API output. Its attribution page requires a 'Powered by Runway' text or logo credit in the UI, which is not the same thing as a burned-in watermark", "source_url": "https://docs.dev.runwayml.com/usage/attribution.md", "source_title": "Runway API — Attribution Requirements", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": "no negativePrompt field in the documented gen4.5 request schema", "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "fps", "price_cn", "open_weights", "license", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "aleph2", "label": "Aleph 2.0", "status": "current", "released_at": "2026-06-02", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 30, "scope": "input videos 2-30s and keyframes up to 30s total. This is a video-EDITING model, not a from-scratch generator", "note": null, "source_url": "https://docs.dev.runwayml.com/api-details/api_changelog/", "source_title": "Runway API Changelog and Updates (2 June 2026)", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "v2v" ], "scope": "input is video plus text or image", "note": null, "source_url": "https://docs.dev.runwayml.com/guides/models.md", "source_title": "Runway API — Models", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/guides/models.md", "source_title": "Runway API — Models", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.28, "currency": "USD" }, "scope": "28 credits per second at $0.01/credit", "note": null, "source_url": "https://docs.dev.runwayml.com/guides/pricing.md", "source_title": "Runway API — Pricing and Costs", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 5, "scope": "up to 5 keyframe images at specific timestamps", "note": null, "source_url": "https://docs.dev.runwayml.com/api-details/api_changelog/", "source_title": "Runway API Changelog and Updates", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "max_resolution", "fps", "native_audio", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "gen4-turbo", "label": "Gen-4 Turbo", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 2, "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "ratio enum 1280:720, 720:1280, 1104:832, 832:1104, 960:960, 1584:672", "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "i2v" ], "scope": "image input ONLY — unlike gen4.5, gen4_turbo has no text-to-video mode; promptImage is required", "note": null, "source_url": "https://docs.dev.runwayml.com/guides/models.md", "source_title": "Runway API — Models", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/guides/models.md", "source_title": "Runway API — Models", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.05, "currency": "USD" }, "scope": "5 credits per second at $0.01/credit", "note": null, "source_url": "https://docs.dev.runwayml.com/guides/pricing.md", "source_title": "Runway API — Pricing and Costs", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://docs.dev.runwayml.com/api.md", "source_title": "Runway API Reference", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "fps", "native_audio", "price_cn", "open_weights", "license", "watermark", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "seedance", "name": "Seedance", "category": "Video & Audio", "website_url": "https://seed.bytedance.com", "entry_url": "https://recatools.com/ai-directory/seedance/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "dreamina-seedance-2-5", "label": "Dreamina Seedance 2.5", "status": "current", "released_at": "2026-06-28", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 30, "scope": "duration accepts [4, 30] or -1 for smart duration (the default). Video-EDITING tasks accept only -1 — you cannot specify an output length there", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 4, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "480p | 720p | 1080p, default 720p. NO 4K on 2.5 — only Seedance 2.0 offers it, so 'Seedance: up to 4K' is wrong for the current flagship. 1080p output is 10-bit H.265, which some players cannot decode", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "generate_audio defaults to TRUE; output audio is always mono regardless of input channels", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v", "s2v" ], "scope": "omni reference takes 0-30 images, 0-10 videos and 0-10 audio clips; 2.5 is the only version accepting audio-ONLY input", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "gated: needs an account balance over USD 30, a USD 30+ AI Savings Plan, or a purchased Seedance resource pack", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.231, "currency": "USD" }, "scope": "vendor's own worked example: 720p 16:9 5s with no video input. 480p $0.103/s, 1080p $0.569/s. Billing is per TOKEN underneath, so reference video raises the bill sharply — 1080p with 30s of input video reaches $11.907 for a 5s output", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1544106", "source_title": "Pricing — ModelArk", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "optional", "scope": "watermark boolean defaults FALSE; true stamps 'AI Generated' bottom-right. This is the BytePlus international endpoint — mainland AIGC labelling obligations attach to the Volcano Engine service instead", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "ap-southeast-1 only", "scope": "base URL ark.ap-southeast.bytepluses.com. Volcano Engine 火山引擎 is the separate mainland-China console for the same models, with different model IDs, pricing and labelling duties", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": "no negative-prompt parameter anywhere in the request body; steering is positive-only", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 30, "scope": "omni reference accepts 1-30. First-frame i2v takes 1 and first+last takes 2, and those modes are MUTUALLY EXCLUSIVE with omni reference", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "dreamina-seedance-2-0", "label": "Dreamina Seedance 2.0", "status": "current", "released_at": "2026-01-28", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": "[4, 15] or -1", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 4, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "4K", "scope": "480p | 720p | 1080p | 4k — the ONLY Seedance version offering 4k, and it is rate-limited far harder (15 RPM, concurrency 1) and encoded 10-bit H.265", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": "omni reference takes 0-9 images, 0-3 videos, 0-3 audio; audio-only input is NOT supported, unlike 2.5", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.15, "currency": "USD" }, "scope": "720p 16:9 5s, no video input. 480p $0.07/s, 1080p $0.37/s, 4K $0.78/s", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1544106", "source_title": "Pricing — ModelArk", "verified_on": "2026-08-20" }, "watermark": { "state": "known", "value": "optional", "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "ap-southeast-1 only", "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 9, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "dreamina-seedance-2-0-fast", "label": "Dreamina Seedance 2.0 Fast", "status": "current", "released_at": "2026-01-28", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 4, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "480p | 720p only — no 1080p and no 4k", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.12, "currency": "USD" }, "scope": "720p 16:9 5s, no video input; 480p $0.06/s. A limited-time 25% discount ran 7 Aug - 7 Sep 2026", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1544106", "source_title": "Pricing — ModelArk", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 9, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "api_available", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "dreamina-seedance-2-0-mini", "label": "Dreamina Seedance 2.0 Mini", "status": "current", "released_at": "2026-06-15", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 4, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "480p | 720p only", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.08, "currency": "USD" }, "scope": "720p 16:9 5s, no video input; 480p $0.04/s. Cheapest Seedance tier; a 60% discount ran 7 Aug - 7 Sep 2026", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1544106", "source_title": "Pricing — ModelArk", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "api_available", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "seedance-1-5-pro", "label": "Seedance 1.5 Pro", "status": "legacy", "released_at": "2025-12-15", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 12, "scope": "[4, 12] or -1", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 4, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "480p | 720p | 1080p, default 720p", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v" ], "scope": "no reference-to-video and no video input — those arrived with 2.0. Uniquely supports a cheap draft mode, re-run from the draft's task ID", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "the only Seedance version also offered on the cheaper flex offline-inference tier", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 2, "scope": "first_frame + last_frame", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "seedance-1-0-pro", "label": "Seedance 1.0 Pro (and 1.0 Pro Fast)", "status": "legacy", "released_at": "2025-05-28", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 12, "scope": "[2, 12] — the only versions reaching down to 2s", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 2, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "480p | 720p | 1080p, and uniquely DEFAULTS to 1080p rather than 720p", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1330310", "source_title": "Model list — ModelArk", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": false, "scope": "generate_audio is supported only on 2.5, the 2.0 series and 1.5 Pro — the 1.0 models are silent-only", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v" ], "scope": "1.0 Pro Fast drops first+last frame — text-to-video and first-frame image-to-video only", "note": null, "source_url": "https://docs.byteplus.com/en/docs/ModelArk/1520757", "source_title": "Create a video generation task — ModelArk", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "api_available", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "sora", "name": "Sora", "category": "Video & Audio", "website_url": "https://sora.com", "entry_url": "https://recatools.com/ai-directory/sora/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "sora-2", "label": "Sora 2", "status": "legacy", "released_at": "2025-09-30", "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 20, "scope": "per generation or per extension. Total length reaches 120s via up to six extensions of an existing video, not in a single create call", "note": null, "source_url": "https://developers.openai.com/api/docs/guides/video-generation", "source_title": "Video generation with Sora — OpenAI API", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 4, 8, 12 ], "scope": "the `seconds` enum on POST /v1/videos, default 4. The hand-written guide additionally claims 16 and 20 are supported; the generated reference enum has not been updated to match", "note": null, "source_url": "https://developers.openai.com/api/reference/resources/videos/methods/create", "source_title": "Create video — OpenAI API Reference", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "720p", "scope": "sora-2 supports only 720x1280 and 1280x720; 1080p exports require sora-2-pro", "note": null, "source_url": "https://developers.openai.com/api/docs/models/sora-2", "source_title": "Sora 2 Model — OpenAI API", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "model card: flagship video generation with synced audio; output modalities are video and audio", "note": null, "source_url": "https://developers.openai.com/api/docs/models/sora-2", "source_title": "Sora 2 Model — OpenAI API", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "v2v" ], "scope": "t2v/i2v via POST /v1/videos; v2v via the extensions and edits endpoints. A character-reference endpoint exists but human-likeness uploads are blocked by default", "note": null, "source_url": "https://developers.openai.com/api/docs/guides/video-generation", "source_title": "Video generation with Sora — OpenAI API", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "⚠️ END OF LIFE. Public and self-serve today, but the Videos API and every sora-2 alias and snapshot are removed on 2026-09-24, with no recommended replacement named. The Sora web and iOS apps were already discontinued on 2026-04-26, so there is no consumer Sora product at all", "note": null, "source_url": "https://developers.openai.com/api/docs/deprecations", "source_title": "Deprecations — OpenAI API", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.1, "currency": "USD" }, "scope": "720x1280 / 1280x720", "note": null, "source_url": "https://developers.openai.com/api/docs/models/sora-2", "source_title": "Sora 2 Model — OpenAI API", "verified_on": "2026-08-20" }, "watermark": { "state": "unpublished", "value": null, "scope": null, "note": "OpenAI documents no watermark policy for API output. The widely-cited rules (watermark on all outputs, removable on Pro) applied to the Sora consumer app, which was discontinued on 2026-04-26", "source_url": "https://developers.openai.com/api/docs/guides/video-generation", "source_title": "Video generation with Sora — OpenAI API", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": "the create-video body has only prompt, model, seconds, size and input_reference", "note": null, "source_url": "https://developers.openai.com/api/reference/resources/videos/methods/create", "source_title": "Create video — OpenAI API Reference", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 1, "scope": "input_reference takes a single file; it must match the target resolution, and images containing human faces are rejected", "note": null, "source_url": "https://developers.openai.com/api/docs/guides/video-generation", "source_title": "Video generation with Sora — OpenAI API", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "fps", "price_cn", "open_weights", "license", "region_availability" ], "constraints": [ { "rule": "The vendor contradicts itself: the generated API reference enumerates `seconds` as 4, 8 and 12 (default 4), while the hand-written guide additionally claims 16 and 20 are supported. max_duration_s follows the guide; duration_choices follows the enum. OpenAI has not reconciled the two pages — treat 16 and 20 as unconfirmed. Separately, the 120s total length is reached via up to six extensions of an existing video, never in one create call.", "affects": [ "max_duration_s", "duration_choices" ], "source_url": "https://developers.openai.com/api/reference/resources/videos/methods/create", "source_title": "POST /v1/videos — `seconds` enum (generated reference), vs the hand-written video-generation guide", "verified_on": "2026-08-20" } ], "oldest_verified_on": "2026-08-20" }, { "id": "sora-2-pro", "label": "Sora 2 Pro", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 4, 8, 12 ], "scope": null, "note": null, "source_url": "https://developers.openai.com/api/reference/resources/videos/methods/create", "source_title": "Create video — OpenAI API Reference", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "1080x1920 / 1920x1080 at $0.70/s. The generated create-video size enum lists only up to 1024x1792 — the model page and the guide are what document 1080p, and the guide states pro is REQUIRED for 1080p exports", "note": null, "source_url": "https://developers.openai.com/api/docs/models/sora-2-pro", "source_title": "Sora 2 Pro Model — OpenAI API", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://developers.openai.com/api/docs/models/sora-2-pro", "source_title": "Sora 2 Pro Model — OpenAI API", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": "⚠️ same 2026-09-24 shutdown as sora-2", "note": null, "source_url": "https://developers.openai.com/api/docs/deprecations", "source_title": "Deprecations — OpenAI API", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.5, "currency": "USD" }, "scope": "1024x1792 / 1792x1024; 1080x1920 / 1920x1080 is $0.70/s — five to seven times the sora-2 rate", "note": null, "source_url": "https://developers.openai.com/api/docs/models/sora-2-pro", "source_title": "Sora 2 Pro Model — OpenAI API", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "fps", "modes", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "stable-video-diffusion", "name": "Stable Video Diffusion", "category": "Video & Audio", "website_url": "https://stability.ai/stable-video", "entry_url": "https://recatools.com/ai-directory/stable-video-diffusion/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "svd-xt-1-1", "label": "Stable Video Diffusion img2vid-XT 1.1", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 4, "scope": "25 frames; the model card lists as a limitation that generated videos are 4 seconds or less", "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1024x576", "scope": null, "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 6, "scope": "the checkpoint is fine-tuned with fixed conditioning at 6 fps. The 24fps figure in circulation came from FILM frame interpolation the retired API applied afterwards, not from the model", "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" }, "native_audio": { "state": "unpublished", "value": null, "scope": null, "note": "no audio capability is mentioned on the model card or the product page; the model is video-only", "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "i2v" ], "scope": "image-to-video ONLY — the card states the model cannot be controlled through text, so it cannot be compared with the rest of this set on prompt adherence at all", "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": false, "scope": "Stability's product page now offers self-hosted deployment via licence only. Confirmed against the live API with a control probe: v2beta/image-to-video returns 404 while v2beta/stable-image/generate/core and v2beta/audio/stable-audio-2/text-to-audio return 401 on the same host — removed, not merely unauthenticated. The 2024 launch post announcing the API is still live and still indexed", "note": null, "source_url": "https://stability.ai/stable-video", "source_title": "Stable Video — Stability AI", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "Stability AI Community License Agreement", "scope": "free for research, non-commercial and commercial use below $1M annual revenue; above that an Enterprise License is required. The older img2vid-xt card carries the earlier stable-video-diffusion-community licence instead", "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card (license)", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": "no text conditioning of any kind exists on this model", "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card (Limitations)", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 1, "scope": null, "note": null, "source_url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1", "source_title": "stabilityai/stable-video-diffusion-img2vid-xt-1-1 — Hugging Face model card", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "price", "price_cn", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "vidu", "name": "Vidu 维度AI", "category": "Video & Audio", "website_url": "https://www.vidu.com", "entry_url": "https://recatools.com/ai-directory/vidu/", "schema": "video/v1", "oldest_verified_on": "2026-08-21", "versions": [ { "id": "viduq3-pro", "label": "Vidu Q3 Pro", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 16, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 1, "scope": "free-form integer 1-16, default 5", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "540p | 720p | 1080p, default 720p", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "audio boolean, Q3 only, defaults TRUE (dialogue plus sound effects). bgm is unavailable on Q3", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v" ], "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.12, "currency": "USD" }, "scope": "1080p PEAK rate (24 credits/s at $0.005/credit); 720p $0.10/s, 540p $0.045/s. Off-peak roughly halves each — Vidu publishes separate peak and off-peak rates, so any single figure needs the qualifier", "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": "documented parameters are prompt, duration, resolution, aspect_ratio, movement_amplitude, style, bgm, audio, seed", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 1, "scope": "image-to-video accepts exactly 1 image; first/last-frame mode takes 2", "note": null, "source_url": "https://platform.vidu.com/docs/image-to-video.md", "source_title": "Image to Video — Vidu API", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "viduq3-turbo", "label": "Vidu Q3 Turbo", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 16, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 1, "scope": "1-16 on t2v/i2v; the reference-to-video endpoint narrows this model to 3-16", "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "audio defaults to TRUE on the Q3 series and emits dialogue plus sound effects; bgm is unavailable on q3. Two qualifiers the earlier scope had wrong: voice_id is documented as \"not effective\" on the Q3 series, and audio_type is accepted but its SPLITTING is documented as supporting \"q2, q1, and 2.0 series models\" only — so on Q3 Turbo you get combined audio and cannot isolate speech or effects. Both caveats are stated on image-to-video; the Subjects-Reference to Video body carries audio_type without them.", "note": null, "source_url": "https://platform.vidu.com/docs/image-to-video.md", "source_title": "Image to Video — Vidu API", "verified_on": "2026-08-22" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v" ], "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.065, "currency": "USD" }, "scope": "1080p peak (13 credits/s); 720p $0.055/s, 540p $0.035/s; off-peak roughly halves", "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "negative_prompt": { "state": "known", "value": false, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 7, "scope": "reference-to-video accepts 1-7; the image-to-video endpoint accepts exactly 1", "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "viduq3-mix", "label": "Vidu Q3 Mix", "status": "current", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 16, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 1, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "720p | 1080p only — unlike Q3 Pro and Turbo, this model offers no 540p", "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "The model emits synchronised audio — the endpoint's own model list describes viduq3-mix as supporting \"simultaneous audio and video output\" — but NOTHING PARAMETERISES IT. reference-to-video.md documents two endpoints: Subjects-Reference to Video carries audio and audio_type but its model enum excludes viduq3-mix, while Reference to Video accepts viduq3-mix and carries no audio field at all (only bgm, which q3 does not support). So on this model audio cannot be switched off, split, or voiced through the API.", "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-22" }, "modes": { "state": "known", "value": [ "ref2v" ], "scope": "Reference-to-video is the only mode this model accepts. The first/last-frame endpoint (start-end-to-video) does not list viduq3-mix among its accepted models, and pricing carries only reference2video rows for Q3-mix.", "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 7, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "viduq2", "label": "Vidu Q2 (q2, q2-pro, q2-turbo)", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 1, "scope": "1-10, default 5", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "the audio parameter defaults to FALSE on Q2 and Q1, against TRUE on Q3 — the same field, opposite default", "note": null, "source_url": "https://platform.vidu.com/docs/image-to-video.md", "source_title": "Image to Video — Vidu API", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v" ], "scope": "v2v on viduq2-pro only, which supports video reference, editing and replacement; with a video attached its reference budget drops from 7 images to 4", "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 7, "scope": "1-7 reference images; 1-4 when a reference video is also supplied", "note": null, "source_url": "https://platform.vidu.com/docs/reference-to-video.md", "source_title": "Reference to Video — Vidu API", "verified_on": "2026-08-21" } }, "absent_fields": [ "duration_choices", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "viduq1", "label": "Vidu Q1", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 5 ], "scope": "5 seconds is the only selectable duration on this model", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "1080p is the only option — Q1 cannot generate 540p or 720p", "note": null, "source_url": "https://platform.vidu.com/docs/text-to-video.md", "source_title": "Text to Video — Vidu API", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 24, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v" ], "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" }, "price": { "state": "known", "value": { "per": "clip", "amount": 0.4, "currency": "USD" }, "scope": "80 credits per 5-second 1080p clip; off-peak is half. Billed per clip, not per second, unlike Q2 and Q3", "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "native_audio", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "vidu-2-0", "label": "Vidu 2.0", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 4, 8 ], "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/image-to-video.md", "source_title": "Image to Video — Vidu API", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "1080p is reachable at 4s only, where image-to-video offers 360p (default), 720p and 1080p; the 8s option is 720p and nothing else. Pricing bills the 4s 1080p clip as a product (\"Vidu 2.0 img2video 4S 1080P\", 100 credits / $0.50), and the model map lists 360p, 720p, 1080p for the family.", "note": null, "source_url": "https://platform.vidu.com/docs/image-to-video.md", "source_title": "Image to Video — Vidu API", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 32, "scope": "the only Vidu model not at 24 fps", "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "i2v", "fl2v", "ref2v" ], "scope": "First/last-frame is reachable: the start-end-to-video endpoint accepts vidu2.0, and pricing bills \"Vidu 2.0 start-end2video\" at four tiers (4s 360p/720p/1080p and 8s 720p). Text-to-video is genuinely absent — that endpoint accepts only viduq3-turbo, viduq3-pro, viduq2 and viduq1. The model map additionally marks Effects/Templates for this model, which is a preset gallery rather than a generation mode and has no code in this vocabulary.", "note": null, "source_url": "https://platform.vidu.com/docs/model-map.md", "source_title": "Model Map — Vidu API", "verified_on": "2026-08-22" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://platform.vidu.com/docs/pricing.md", "source_title": "Pricing — Vidu API", "verified_on": "2026-08-21" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "native_audio", "price", "price_cn", "open_weights", "license", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-21" } ] }, { "slug": "wan-video", "name": "Wan 通义万相", "category": "Video & Audio", "website_url": "https://tongyi.aliyun.com/wanxiang", "entry_url": "https://recatools.com/ai-directory/wan-video/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "wan2-7", "label": "Wan 2.7", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": "t2v and i2v 2-15s; the r2v and videoedit endpoints cap at 10s", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 2, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "720P | 1080P, default 1080P on i2v. No 480P tier on 2.7, unlike Wan 2.5 and Wan 3.0", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 30, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "generates dubbing when no audio is supplied; an audio_url may instead be passed as a lip-sync driver", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v", "v2v", "s2v" ], "scope": "split across four model IDs — wan2.7-t2v, -i2v, -r2v, -videoedit. Request shapes differ from the 2.6 'legacy protocol' and are not interchangeable", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.15, "currency": "USD" }, "scope": "1080P; 720P $0.10/s. Same rate across t2v, i2v, r2v and videoedit. 50s free quota, Singapore only. r2v and videoedit bill INPUT video duration in addition to output", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": false, "scope": "the Wan-Video GitHub organisation publishes model repositories for 2.1 and 2.2 only — there is no 2.5, 2.6, 2.7 or 3.0 weights repository. 'Wan is open source' is true of the 2022-2.2 line and false of everything currently sold", "note": null, "source_url": "https://github.com/orgs/Wan-Video/repositories", "source_title": "Wan-Video — GitHub repositories", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": "negative_prompt, maximum 500 characters", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "max_input_images": { "state": "known", "value": 2, "scope": "first_frame + last_frame on wan2.7-i2v", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/image-to-video-general-api-reference", "source_title": "Wan 2.7 image-to-video API — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price_cn", "license", "watermark", "region_availability" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "wan3-0-video", "label": "Wan 3.0", "status": "preview", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 30, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 2, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "480P | 720P | 1080P", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 30, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "ref2v" ], "scope": "documented as all-in-one reference — images, videos and audio, plus docx/ppt/pdf files and web links as input", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": false, "scope": "flagged Invitational Preview on the price list — the endpoint exists but access is gated, not self-serve. Do not present Wan 3.0 as generally available", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.2, "currency": "USD" }, "scope": "1080P; 720P $0.10/s, 480P $0.05/s. Billed on input plus output video duration combined, not output alone", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" }, "region_availability": { "state": "known", "value": "Singapore and China (Beijing) only", "scope": "narrower than the rest of the Wan line, which the same price page also lists in Frankfurt, Virginia and Tokyo. The 30s free quota applies in Singapore only", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license", "watermark", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "wan2-6", "label": "Wan 2.6", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 15, "scope": "t2v/i2v 2-15s; r2v 2-10s. The US-scoped fork wan2.6-t2v-us accepts only 5 and 10 — same version number, different spec, purely by region", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "min_duration_s": { "state": "known", "value": 2, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 30, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": "wan2.6 and wan2.5 generate audio by default; on the -flash variants audio is a priced toggle and audio=false halves the rate", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "ref2v" ], "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.15, "currency": "USD" }, "scope": "1080P; 720P $0.10/s. The -flash variants are far cheaper: wan2.6-i2v-flash is $0.075/s at 1080p with audio, $0.0375/s silent", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" } }, "absent_fields": [ "duration_choices", "price_cn", "open_weights", "license", "watermark", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "wan2-5-preview", "label": "Wan 2.5", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "duration_choices": { "state": "known", "value": [ 5, 10 ], "scope": "a fixed set — 2.5 cannot do free-form durations, unlike 2.6 and 2.7", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "480P | 720P | 1080P, default 1920x1080", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 30, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.15, "currency": "USD" }, "scope": "1080P; 720P $0.10/s, 480P $0.05/s", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference", "source_title": "Wan2.7 Text-to-Video API Reference — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "api_available", "price_cn", "open_weights", "license", "watermark", "region_availability", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "wan2-2", "label": "Wan 2.2 (open weights, and the hosted -plus / -flash endpoints)", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "duration_choices": { "state": "known", "value": [ 5 ], "scope": "the hosted t2v/i2v/kf2v endpoints are fixed at 5 seconds. The separate wan2.2-animate-move / -animate-mix character-animation endpoints run 2-30s at 15/25 fps", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1080p", "scope": "hosted wan2.2-t2v-plus is 480P and 1080P (no 720P); -i2v-flash and -kf2v-flash add 720P. The OPEN checkpoint is a different configuration — its own repo documents 480P and 720P, with TI2V-5B at 720P", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 30, "scope": "hosted API. The open TI2V-5B checkpoint is documented at 24 fps — the served model and the downloadable model are NOT the same configuration", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "native_audio": { "state": "known", "value": false, "scope": "'No audio' on every hosted wan2.2 video endpoint; the open S2V-14B checkpoint is speech-DRIVEN (audio in), not audio-generating", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model", "source_title": "Video generation and editing — Alibaba Cloud Model Studio", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v", "s2v" ], "scope": "s2v is open-weights only (S2V-14B); the hosted endpoints are t2v/i2v/kf2v plus the animate pair", "note": null, "source_url": "https://github.com/Wan-Video/Wan2.2", "source_title": "Wan-Video/Wan2.2 — Open and Advanced Large-Scale Video Generative Models", "verified_on": "2026-08-20" }, "price": { "state": "known", "value": { "per": "second", "amount": 0.1, "currency": "USD" }, "scope": "hosted wan2.2-t2v-plus at 1080P; 480P $0.02/s. wan2.2-i2v-flash is $0.036/s at 720P. Zero if you self-host the open weights", "note": null, "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "source_title": "Alibaba Cloud Model Studio model pricing", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": "five checkpoints: T2V-A14B, I2V-A14B, TI2V-5B, S2V-14B, Animate-14B. This is the NEWEST open Wan release — 2.5 onward is API-only", "note": null, "source_url": "https://github.com/Wan-Video/Wan2.2", "source_title": "Wan-Video/Wan2.2 — Open and Advanced Large-Scale Video Generative Models", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "Apache-2.0", "scope": null, "note": null, "source_url": "https://github.com/Wan-Video/Wan2.2", "source_title": "Wan-Video/Wan2.2 — Open and Advanced Large-Scale Video Generative Models", "verified_on": "2026-08-20" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "api_available", "price_cn", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] }, { "slug": "zhipu-qingying", "name": "Zhipu Qingying 智谱清影 (CogVideoX)", "category": "Video & Audio", "website_url": "https://chatglm.cn", "entry_url": "https://recatools.com/ai-directory/zhipu-qingying/", "schema": "video/v1", "oldest_verified_on": "2026-08-20", "versions": [ { "id": "cogvideox-3", "label": "CogVideoX-3 (hosted)", "status": "current", "released_at": null, "is_flagship": true, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "min_duration_s": { "state": "known", "value": 5, "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "duration_choices": { "state": "known", "value": [ 5, 10 ], "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "max_resolution": { "state": "known", "value": "4K", "scope": "the size enum is a fixed list — 1280x720, 720x1280, 1024x1024, 1920x1080, 1080x1920, 2048x1080, 3840x2160. 4K means that last member, not arbitrary resolution", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 60, "scope": "enum 30 or 60, default 30", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "native_audio": { "state": "known", "value": true, "scope": "with_audio defaults to false, and the docs describe it as 生成 AI 音效 — sound effects, not dialogue or speech", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v", "fl2v" ], "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/cn/guide/models/video-generation/cogvideox-3.md", "source_title": "CogVideoX-3 — 智谱AI开放文档 (输入模态)", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/cn/guide/models/video-generation/cogvideox-3.md", "source_title": "CogVideoX-3 — 智谱AI开放文档", "verified_on": "2026-08-21" }, "price_cn": { "state": "known", "value": { "per": "clip", "amount": 1, "currency": "CNY" }, "scope": "1 元/次 on the CN platform bigmodel.cn — flat per call regardless of duration or resolution. The international platform z.ai prices the SAME model id at $0.2/video", "note": null, "source_url": "https://docs.bigmodel.cn/cn/guide/models/video-generation/cogvideox-3.md", "source_title": "CogVideoX-3 — 智谱AI开放文档 (价格)", "verified_on": "2026-08-21" }, "watermark": { "state": "known", "value": "optional", "scope": "watermark_enabled defaults TRUE and applies both a visible AI mark and an implicit digital watermark, described as 符合政策要求. Turning it off requires a signed disclaimer through 个人中心-安全管理-去水印管理 — not freely switchable", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "region_availability": { "state": "known", "value": "global, on two separately-billed platforms", "scope": "bigmodel.cn for CN in CNY and docs.z.ai internationally in USD — same model id, different endpoint host and price", "note": null, "source_url": "https://docs.z.ai/guides/video/cogvideox-3", "source_title": "CogVideoX-3 Overview — Z.AI Developer Document", "verified_on": "2026-08-20" }, "negative_prompt": { "state": "known", "value": false, "scope": "read against the full request schema — no negative-prompt parameter exists on any video model on the platform", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 2, "scope": "first/last-frame mode: first image is the first frame, second is the last; each at most 5MB", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" } }, "absent_fields": [ "price", "open_weights", "license" ], "constraints": [], "oldest_verified_on": "2026-08-20" }, { "id": "cogvideox-2", "label": "CogVideoX-2 (hosted)", "status": "legacy", "released_at": null, "is_flagship": false, "fields": { "max_resolution": { "state": "known", "value": "4K", "scope": "size enum 720x480, 1024x1024, 1280x960, 960x1280, 1920x1080, 1080x1920, 2048x1080, 3840x2160", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "fps": { "state": "known", "value": 60, "scope": "enum 30 or 60", "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": "single input image only — no first/last-frame mode, unlike CogVideoX-3", "note": null, "source_url": "https://docs.bigmodel.cn/cn/guide/models/video-generation/cogvideox-2.md", "source_title": "CogVideoX-2 — 智谱AI开放文档", "verified_on": "2026-08-21" }, "api_available": { "state": "known", "value": true, "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/cn/guide/models/video-generation/cogvideox-2.md", "source_title": "CogVideoX-2 — 智谱AI开放文档", "verified_on": "2026-08-21" }, "price_cn": { "state": "known", "value": { "per": "clip", "amount": 0.5, "currency": "CNY" }, "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/cn/guide/models/video-generation/cogvideox-2.md", "source_title": "CogVideoX-2 — 智谱AI开放文档 (0.5 元 / 次)", "verified_on": "2026-08-21" }, "max_input_images": { "state": "known", "value": 1, "scope": null, "note": null, "source_url": "https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E8%A7%86%E9%A2%91%E7%94%9F%E6%88%90%E5%BC%82%E6%AD%A5.md", "source_title": "视频生成(异步) — 智谱AI开放文档 API 参考 (OpenAPI)", "verified_on": "2026-08-21" } }, "absent_fields": [ "max_duration_s", "min_duration_s", "duration_choices", "native_audio", "price", "open_weights", "license", "watermark", "region_availability", "negative_prompt" ], "constraints": [], "oldest_verified_on": "2026-08-21" }, { "id": "cogvideox1-5-5b", "label": "CogVideoX1.5-5B (open checkpoint)", "status": "legacy", "released_at": "2024-11-08", "is_flagship": false, "fields": { "max_duration_s": { "state": "known", "value": 10, "scope": "5-10s; frame counts must satisfy 16N+1 with N at most 10", "note": null, "source_url": "https://github.com/zai-org/CogVideo", "source_title": "zai-org/CogVideo — README (model table)", "verified_on": "2026-08-20" }, "max_resolution": { "state": "known", "value": "1360x768", "scope": "the I2V variant accepts variable resolution with a minimum side of 768 and a maximum of 1360", "note": null, "source_url": "https://github.com/zai-org/CogVideo", "source_title": "zai-org/CogVideo — README (model table)", "verified_on": "2026-08-20" }, "fps": { "state": "known", "value": 16, "scope": null, "note": null, "source_url": "https://github.com/zai-org/CogVideo", "source_title": "zai-org/CogVideo — README (model table)", "verified_on": "2026-08-20" }, "modes": { "state": "known", "value": [ "t2v", "i2v" ], "scope": null, "note": null, "source_url": "https://github.com/zai-org/CogVideo", "source_title": "zai-org/CogVideo — README", "verified_on": "2026-08-20" }, "open_weights": { "state": "known", "value": true, "scope": "this is the NEWEST open checkpoint — there are no open weights for CogVideoX-2 or CogVideoX-3, so 'CogVideoX is open source' is true of the 2024 line and false of everything currently sold. The repo also MOVED, from THUDM/CogVideo to zai-org/CogVideo", "note": null, "source_url": "https://github.com/zai-org/CogVideo", "source_title": "zai-org/CogVideo — README", "verified_on": "2026-08-20" }, "license": { "state": "known", "value": "CogVideoX LICENSE", "scope": "the 5B-class T2V and I2V transformer weights are under the bespoke CogVideoX LICENSE; only the smaller CogVideoX-2B is Apache-2.0", "note": null, "source_url": "https://github.com/zai-org/CogVideo", "source_title": "zai-org/CogVideo — README (model table, license column)", "verified_on": "2026-08-20" } }, "absent_fields": [ "min_duration_s", "duration_choices", "native_audio", "api_available", "price", "price_cn", "watermark", "region_availability", "negative_prompt", "max_input_images" ], "constraints": [], "oldest_verified_on": "2026-08-20" } ] } ] }