Nous Research API Pricing
Nous Research builds the open-weight Hermes series — steerable, instruction-tuned fine-tunes of Llama with strong function-calling and minimal refusals. A favourite of the open-source community for agents and self-hosting.
Models
4 tracked
All tiers, latest pricing.
All Nous Research Models
| Model | Tier | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| Hermes 4 70B | flagship | $0.130 | $0.400 | 131K |
| Hermes 3 70B Instruct | flagship | $0.700 | $0.700 | 131K |
| Hermes 4 405B | flagship | $1.00 | $3.00 | 131K |
| Hermes 3 405B Instruct | flagship | $1.00 | $1.00 | 131K |
Model Details
Hermes 4 70B
$0.130 inHermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B.
Hermes 3 70B Instruct
$0.700 inHermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence.
Hermes 4 405B
$1.00 inHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.
Hermes 3 405B Instruct
$1.00 inHermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence.
Calculate Nous Research API Costs
Use the TokenRate calculator to estimate exactly what Nous Research models will cost for your workload.
Open Calculator →Other Providers