Nous Research models
Nous Research has 4 models in the directory. The newest is Hermes 4 Large, released Aug 26, 2025.
The cheapest to run is Hermes 2 Pro Llama 3 8B at $0.14 per million input tokens.
Hermes 4 Large has the longest context window, 128K tokens.
- Models
- 4
- Newest
- Aug 26, 2025
- From
- $0.14/M input
- Longest context
- 128K
All Nous Research models
Filter in the directory- 128K context
Reads text. Tool calling, structured output. Served by 4 providers.
by nousresearchAug 26, 2025$0.30/M input tokens$1.20/M output tokens4 providers
- 66K context
Reads text. Tool calling, structured output. Served by 4 providers.
by nousresearchAug 18, 2024$0.70/M input tokens$0.70/M output tokens4 providers
- 128K context
Reads text. Tool calling, structured output. Served by 4 providers.
by nousresearchAug 16, 2024$1/M input tokens$1/M output tokens4 providers
- 8K context
Reads text. Tool calling, structured output. Served by 2 providers.
by nousresearchApr 30, 2024$0.14/M input tokens$0.14/M output tokens2 providers
Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.
Not sure which Nous Research model fits?
I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.
Book Meeting