Hermes 4 405B
Nous Research · nousresearch/hermes-4-405b
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Hermes 4 405B ranks #242 of 377 models in the default AI Benchmark Hub order (quality first, then cost). At $2.00 blended per million tokens, it is cheaper than 35% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 117964
Pricing
Output / 1M: 3.00
Blend / 1M: 2.00
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $2.00per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $2.00 |
| 10,000,000 | $20.00 |
| 100,000,000 | $200.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
Closest API price
- Relace Search$2.00 / 1M
- Pareto 26.10$2.00 / 1M
- Pareto Latest$2.00 / 1M
- Nova Pro 1.0$2.00 / 1M
- Qwen3 235B A22B Thinking 2507$1.98 / 1M