Hermes 4 70B
Open weightNous Research · Released August 2025 · Knowledge cutoff August 2024
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...
Facts and pricing
- Provider
- Nous Research
- Context window
- 131K tokens
- Input price
- 1.4 credits / 1M tokens ($0.13 raw)
- Output price
- 4.4 credits / 1M tokens ($0.40 raw)
- Vision (image input)
- No
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Hermes 4 70B now
What Hermes 4 70B is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
Nous Research family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Hermes 4 70B | 131K | 1.4 | 4.4 | August 2025 |
| Hermes 4 405B | 131K | 11.0 | 33.0 | August 2025 |
| Hermes 3 70B Instruct | 131K | 7.7 | 7.7 | August 2024 |
| Hermes 3 405B Instruct (free) | 131K | 0 | 0 | August 2024 |
| Hermes 3 405B Instruct | 131K | 11.0 | 11.0 | August 2024 |
Frequently asked questions
- What is Hermes 4 70B?
- Hermes 4 70B is an AI model by Nous Research. 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...
- How much does Hermes 4 70B cost on Zeplik?
- Input tokens cost 1.4 credits per million and output tokens 4.4 credits per million (1 credit = $0.10; the raw provider rates are $0.13 and $0.40 per million). New accounts start with free credits.
- How long can a conversation with Hermes 4 70B be?
- Hermes 4 70B has a 131K-token context window (131,072 tokens), which covers the conversation plus any documents you attach.
- Does Hermes 4 70B support images and tools?
- Hermes 4 70B is text-only and does not support tool calling.
Related models
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 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Hermes 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, and improvements across the...
Hermes 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, and improvements across the...
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...