Nous: Hermes 4 405B pricing and limits

id nousresearch/hermes-4-405b · listed 2025-08-26 · knowledge cutoff 2024-08-31

Input (per 1M tokens)	$1.000
Output (per 1M tokens)	$3.000
Context window	131,072 tokens
Max output	117,964 tokens
Modalities	text → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $1.90.

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...

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
Meta: Llama 4 Scout	$0.100	$0.300	1,310,720
OpenAI: GPT-6 Luna Pro	$0.100	$0.500	1,050,000
OpenAI: GPT-6 Luna Pro (batch)	$0.050	$0.250	1,050,000

Other nousresearch models

Nous: Hermes 3 70B Instruct ($0.700 / $0.700) · Nous: Hermes 3 405B Instruct ($1.000 / $1.000)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=nousresearch/hermes-4-405b (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=nousresearch. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with nousresearch. Agent Exchange