Hermes 4 405B: API pricing, providers and specs
Hermes 4 405B is a text model by Nous Research. 4 providers serve it, from $3 to $3.17 /1M; the lowest price is at OpenRouter.
How Hermes 4 405B compares
Against the 737 text models on the site priced the same way.
- Pricey for its class: at $3 /1M, its lowest price is above 70% of comparable models (median $1.10).
- Its 131K-token context window is larger than 21% of them (median 262K), about 200 pages of text.
- 4 providers serve it; 60% of comparable models have fewer.
- Its weights are open under the Llama 3 license: commercial use under the maker's terms.
Hermes 4 405B prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| OpenRouter | $1/1M | From$3/1M | — | 131K |
 Requesty | $1/1M | From$3/1M | $1/1M | 128K |
 Cortecs | $1/1M | $3/1M | — | — |
| AI/ML API | $1.06/1M | $3.17/1M | $1.06/1M | — |
- OpenRouterFrom$3
- RequestyFrom$3
- Cortecs$3
- AI/ML API$3.17
Specs
- Type
- Text
- Maker
- Nous Research
- Inputs
- Text
- Outputs
- Text
- Context
- 131K≈ 200 pages of text
- Max output
- 118K
- Capabilities
- JSON, Reasoning
- Released
- Aug 6, 2025
- License
- Llama 3commercial use under the maker's terms
- Open weights
- Yes, downloadable
- Parameters
- 406B
Alternatives to Hermes 4 405B
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Hermes 4 405Bthis model | $3/1M | 131K | — | 4 |
 Gemini 4 Argon | $8/1M | 1.05M | 1673 | 26 |
| Kimi K3 | $8.28/1M | 1.05M | 1655 | 47 |
| GPT-6.1 Sol | $8/1M | 1.05M | 1749 | 27 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
| GPT-6 Sol | $8/1M | 1.05M | 1682 | 28 |
 Qwen3.8 2.4T A95B | $4.11/1M | 1M | — | 22 |
| Grok 4.7 | $4.80/1M | 500K | 1637 | 28 |
| Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
More from Nous Research
Hermes 4 405B FAQ
The lowest price for Hermes 4 405B is $3 /1M, at OpenRouter.
OpenRouter, at $3 /1M. 4 providers serve Hermes 4 405B; the table above lists every one with its price.
Hermes 4 405B reads up to 131K tokens per request and writes up to 118K.
Yes. Hermes 4 405B's weights can be downloaded from its maker's Hugging Face page, under the Llama 3 license.
About 406B, as the safetensors metadata of its official Hugging Face repo states.
4 API providers serve Hermes 4 405B. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us