Nousresearchhermes-4-405b

Nous: Hermes 4 405B API Pricing

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...

Base Input Price$1.00/ 1M tokens

Base Output Price$3.00/ 1M tokens

Prompt Cache Read$0.200-80% discount

Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates

Provider Name	Input / 1M	Output / 1M	Prompt Caching	Access Endpoint
Nousresearch Direct	$1.00	$3.00	Supported	Connect
OpenRouter	$1.00	$3.00	Supported	Connect

Head-to-Head Comparisons for Nous: Hermes 4 405B

Nous: Hermes 4 405B vs OpenAI: GPT-6.1 Sol$1/M vs $2/M

Nous: Hermes 4 405B vs GPT-4o (Omni)$1/M vs $2.5/M

Nous: Hermes 4 405B vs Claude 3.5 Sonnet$1/M vs $3/M

Nous: Hermes 4 405B vs DeepSeek-V3 (deepseek-chat)$1/M vs $0.27/M