Hermes 4 70B
Nous Research · nousresearch/hermes-4-70b
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...
Hermes 4 70B ranks #114 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.27 blended per million tokens, it is cheaper than 77% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
open weightstexttext->text
Context
Max context: 131072
Max output: 117964
Max output: 117964
Pricing
Input / 1M: 0.13
Output / 1M: 0.40
Blend / 1M: 0.27
Output / 1M: 0.40
Blend / 1M: 0.27
Quality
Quality index: —
Provider
Provider: Nous Research
Moderated: no
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.27per 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 | $0.27 |
| 10,000,000 | $2.65 |
| 100,000,000 | $26.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Nous Research
- Hermes 3 70B Instruct$0.70 / 1M
- Hermes 3 405B Instruct$1.00 / 1M
- Hermes 4 405B$2.00 / 1M
Closest API price
- Gemma 3 27B$0.26 / 1M
- Qwen3 VL 32B Instruct$0.26 / 1M
- Seed-2.0-Mini$0.25 / 1M
- Gemini 2.5 Flash Lite$0.25 / 1M
- GPT-4.1 Nano$0.25 / 1M