Nous Research · language model
Hermes 3 70B Instruct: pricing, context and benchmarks
Hermes 3 70B Instruct is a language model from Nous Research released on August 18, 2024. It costs $0.7 per million input tokens and $0.7 per million output tokens, with a 131.1K-token context window. No independent score has been published for it so far.
| Price | 16/30 | |
|---|---|---|
| Context | 4/15 | |
| Features | 7/15 |
What you need to know about Hermes 3 70B Instruct
Hermes 3 70B Instruct was released by Nous Research (United States) on August 18, 2024. It accepts text as input and produces text. Its context window reaches 131,072 tokens, larger than 29 % of the models in the registry, and it can write up to 16,384 tokens in one go.
Released more than 2 years ago, it belongs to a generation most vendors have since superseded.
Hermes 3 70B Instruct pricing
On OpenRouter, Hermes 3 70B Instruct costs $0.7 per million input tokens and $0.7 per million output tokens. Counting three tokens read for every token written, its average price is $0.7 per million, more expensive than 48 % of paid models (1.1 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0018. At 1,000 tasks a day, budget $53 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Hermes 3 70B Instruct. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at December 2023.
Its weights are open and downloadable from Hugging Face: you can run it on your own machines without sending your data to a third party.
Other Nous Research models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Hermes 4 405B | Aug 26, 2025 | $1.5 | — |
| Hermes 3 405B Instruct | Aug 16, 2024 | $1 | — |
Verdict
Hermes 3 70B Instruct scores 45/100 on our grid, which only uses published figures.
Strengths
- Open weights: self-hostable, your data stays with you.
Limitations
- No tool calling: unusable as an agent's brain.
- No independent score published: performance cannot be verified.
- Older generation, often replaced by a newer model from the same vendor.
- Text only: reads neither images nor files.
Avoid if…
- you are building an agent that must call tools.
Alternatives
- Mistral Medium 3$0.8
- Mistral Medium 3.1$0.8
- Command A+$0.6
- Muse Glimmer 30B$0.53
- Llama 3.1 Euryale 70B v2.2$0.85
- Aion-3.0-Mini$0.88
Comparisons and tools
Learn more
Frequently asked questions
How much does Hermes 3 70B Instruct cost?
$0.7 per million input tokens and $0.7 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0018.
How big is Hermes 3 70B Instruct's context window?
131,072 tokens, roughly 98,000 words, with a maximum of 16,384 output tokens.
Can Hermes 3 70B Instruct run locally?
Yes, its weights are published.
Is Hermes 3 70B Instruct suitable for an AI agent?
No: without tool calling it cannot act, only answer.
What are the alternatives to Hermes 3 70B Instruct?
The closest models on price and performance are Mistral Medium 3, Mistral Medium 3.1, and Command A+.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score