Nous: Hermes 4 405B
by Nousresearchtext->text1 endpoint
Overview
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Capabilities
Text generation
Structured output
Extended reasoning
Long context
Top-P sampling
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
131.1K tokens
Max Output
118.0K tokens
Knowledge Cutoff
2024-08-31
Tokenizer
Other
Uptime (24h)
10000.0%
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p
Pricing
Per 1M tokens
Input$1.00
Output$3.00
Added
August 26, 2025
Last synced 9/18/2026