Nous: Hermes 3 70B Instruct
Analysis Summary
Nous Hermes 3 70B Instruct is a fine-tuned model from Nous Research, built on a 70B base with a 131K context window. Its intelligence index of 5.1 and MMLU Pro score of 0.571 place it in the lower-mid tier, with no tool use, function calling, or vision support.
For businesses, it suits general text generation and content tasks where structured output or multimodal capability is not required. The large context window is a positive for long-document summarisation, but the absence of tool use and function calling means it cannot participate in agentic or API-driven workflows without significant additional engineering.
At $0.70 per million tokens for both input and output, pricing is reasonable but not exceptional given the capability level. Teams specifically interested in Nous Research fine-tunes for instruction following or roleplay-adjacent tasks may find value here, but for general business use, models with tool use and stronger benchmarks are preferable at similar price points.
Assessed June 17, 2026
Editorial notes
Nous Hermes 3 70B Instruct offers reasonable general reasoning at a moderate price, but lacks tool use, vision, and function calling, limiting its utility for structured business workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Nous: Hermes 3 70B Instruct compares
Nous: Hermes 3 70B Instruct ranks #305 of 380 AI models we track for overall intelligence. Its 131K-token context window is larger than 59% of the models we list. At $0.70 per million input tokens it is cheaper than 29% of comparable models.
About Nous: Hermes 3 70B Instruct
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..
Architecture Detail
| Instruct Type | chatml |
Benchmark Scores
Intelligence
Technical
Benchmark data from Artificial Analysis and Hugging Face
How does Nous: Hermes 3 70B Instruct stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
nousresearch/hermes-3-llama-3.1-70b
|
| Provider | nousresearch |
| Release Date | August 18, 2024 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.70 | $0.000700 |
| Output | $0.70 | $0.000700 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Nous: Hermes 3 70B Instruct
How much does Nous: Hermes 3 70B Instruct cost?
Nous: Hermes 3 70B Instruct costs $0.70 per million input tokens and $0.70 per million output tokens.
What is the context window of Nous: Hermes 3 70B Instruct?
Nous: Hermes 3 70B Instruct has a context window of 131,072 tokens (131K).
Who created Nous: Hermes 3 70B Instruct?
Nous: Hermes 3 70B Instruct is developed by Nous and was released on August 18, 2024.
