Nous Hermes vs OpenHermes
A side-by-side look at scores, pricing and features — with RECATOOLS' ASEAN-aware verdict for each.
Nous Hermes
Nous Research's steerable open-weight models, now Hermes 4 and 4.3
Visit
|
OpenHermes
Teknium's Mistral 7B fine-tune — 2023's go-to local chat model
Visit
|
|
|---|---|---|
| RECATOOLS Score | 6.8 / 10 | 5.9 / 10 |
| Capability | ||
| Value for money | ||
| Ease of use | ||
| ASEAN readiness | ||
| API quality | ||
| Pricing | Open Source | Open Source |
| Free tier | Open weights free to download and run, under Apache 2.0 or the Llama 3 licence depending on the model | Fully free |
| Paid from | Free weights, or hosted Hermes 4 405B on OpenRouter from $1 per million input tokens | — |
| Has API | ✓ | ✗ |
| Open source | ✓ | ✓ |
| Free to use | ✓ | ✓ |
| Users | 500k+ downloads | 500k+ downloads |
| Founded | 2023 | — |
| Maker | Nous Research, Inc. | Nous Research |
| Verdict | Hermes remains the open-weight line to reach for when you want a model that follows your own system prompt: Hermes 4 brought hybrid reasoning in 14B, 70B and 405B sizes, and Hermes 4.3 squeezes similar quality into 36B w... |
OpenHermes 2.5 (Mistral-7B) by Teknium is a widely respected open fine-tune that became a go-to general-purpose 7B model, noted for solid instruction-following, conversation and a notable coding bump from its training mi... |
| Full review → | Full review → |
← Back to AI Directory
Comparisons cover up to 4 tools. Scores are RECATOOLS editorial assessments; verify current pricing on each vendor's site.