All AI models · LLM benchmarks · Methodology

Nous Research

Hermes 3 70B

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...

Model facts

Context window
131K tokens
Maximum output
16K tokens
Cheapest paid input
$0.408 per 1M tokens
Cheapest paid output
$0.408 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

tool calling, structured output, temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.408 input / $0.408 output per 1M tokens

API providers

  • NanoGPT — model id NousResearch/hermes-3-llama-3.1-70b; $0.408 input / $0.408 output per 1M tokens; provider documentation
  • OpenRouter — model id nousresearch/hermes-3-llama-3.1-70b; $0.7 input / $0.7 output per 1M tokens; provider documentation