N
Hermes 4 70BOPEN
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B.
Prices update automatically — checked daily against provider list prices.
- $0.2 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 62% of the 191 open-weight models tracked here
- 1 of 4 Nous Research models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Hermes 4 70B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, Hermes 4 70B delivers 7.9 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.2 per 1M tokens (median of 23) — this one costs $0.2.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 23 more
About this model
Hermes 4 70B is an open-weight AI model by Nous Research. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Hermes 4 70B?
Hermes 4 70B is an AI language model from Nous Research. It is open-weight: you can download it and run it on your own hardware, for free. It scores 9.9 on the Artificial Analysis intelligence index.
Is Hermes 4 70B free?
The weights are free and open — you can self-host Hermes 4 70B and pay nothing per token. If you prefer a hosted API, list prices are $0.13 per million input tokens and $0.4 per million output tokens.
What is Hermes 4 70B good at?
Independent benchmarks from Artificial Analysis give it GPQA 69.9%, MMLU-Pro 81.1%, Humanity's Last Exam 8.8%, Long Context Reasoning 8%, LiveCodeBench 65.3%, SciCode 34.1%, AIME 2025 68.7%, IFBench 31.3%, τ²-Bench 22.5%, Terminal-Bench Hard 4.5%. It is particularly used for mathematical reasoning.
How fast is Hermes 4 70B?
It generates about 86.8 tokens per second, with a median 0.6s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Hermes 4 70B?
Yes. Hermes 4 70B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.