All ModelschatHermes 4 70B

Hermes 4 70B

Name: Hermes 4 70B
Availability: InStock
Author: Nous Research

by Nous ResearchFast

Efficient uncensored reasoning model from Nous Research — hybrid think/respond mode, low refusal rates, strong at math, code, and structured output

Detailed content for this model is coming soon.

Input$0.169 per 1M tokens

Output$0.52 per 1M tokens

Context Window131K

Streaming Yes

Vision No

Reasoning No

Tool Use No

ProviderNous Research

Similar Models

Z-AI

Lightweight GLM model

OpenAI

Fast, cost-efficient reasoning model

DeepSeek

Legacy — maps to V4 Flash non-thinking mode. Deprecated 2026-07-24.