Hermes 4 70B

nousresearch

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 respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.

Try Now

Capabilities

Extended Thinking

Example Use Cases

Hybrid reasoning with tool use

Mid-tier math or coding with thinking

Structured output with reasoning

Technical Specifications

Context Window

131,072 tokens

Max Output

131,072 tokens

Cache Miss Cost

$0.11 per 1M tokens

Non-Reasoning Cost

$0.38 per 1M tokens

Cache Read Cost

$0.055 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus