Hermes 4 70B

Open weight

Nous 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

Ask Hermes 4 70B anything. Your prompt opens in the Zeplik app with this model selected.

Hermes 4 70B

What Hermes 4 70B is best for

Nous Research family

ModelContextInput cr/MOutput cr/MReleased
Hermes 4 70B131K1.44.4August 2025
Hermes 4 405B131K11.033.0August 2025
Hermes 3 70B Instruct131K7.77.7August 2024
Hermes 3 405B Instruct (free)131K00August 2024
Hermes 3 405B Instruct131K11.011.0August 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 405BOpen weight

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...

131K ctx33.0 cr/M outAugust 2025
Hermes 3 70B InstructOpen weight

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...

131K ctx7.7 cr/M outAugust 2024
Hermes 3 405B Instruct (free)Open weight

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...

131K ctx0 cr/M outAugust 2024
Hermes 3 405B InstructOpen weight

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...

131K ctx11.0 cr/M outAugust 2024
GPT-5.6 Luna ProFrontier

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

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

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...

1.1M ctx66.0 cr/M outJuly 2026
Hermes 4 70B - Nous Research AI Model | Zeplik Chat