Hermes 4 (Thinking) model ID, context window & pricing
nousresearch
Quick facts
Model ID NousResearch/Hermes-4-70B:thinking
Source NanoGPT
Context Window 128000
Pricing $0.20 input / $0.40 output per 1M tokens
Capabilities open weights
Model overview
Hermes 4 (Thinking) is an AI model from NanoGPT with 128000 token context window and text input support.
Published pricing is $0.20 input and $0.40 output per 1M tokens.
- Workloads that use text inputs with text outputs.
Model ID NousResearch/Hermes-4-70B:thinking
Provider NanoGPT
Family nousresearch
Status -
Knowledge Cutoff -
Release Date 2025-09-17
Input Modalities text
Output Modalities text
Context Window 128000
Input Limit 128000
Output Limit 8192
Tool Calling No
Reasoning No
Structured Output No
Temperature Control -
Open Weights Yes
Input Cost / 1M tokens $0.20
Output Cost / 1M tokens $0.40
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.10
Cache Write Cost / 1M tokens -