Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index
nousresearch
nousresearch
FrontierAUTO PROFILELIVE INDEX

Nous: Hermes 3 405B Instruct (free)

text->text

Nous: Hermes 3 405B Instruct (free) is a community fine-tune. Behaviour and benchmarks track the upstream base model the fine-tune was trained from. Available via nousresearch. 131K-token context. Free tier on OpenRouter. Inherits weights from an upstream open-weights base; benchmarks track the base model unless the fine-tuner publishes their own. Routed through OpenRouter's free tier — capacity is best-effort.

Nous: Hermes 3 405B Instruct (free) is a frontier AI model from nousresearch. It costs $0.000 per million input tokens and $0.000 per million output tokens (blended $0.000/M), with a 131K-token context window.

Modalities textPricing source ↗Compare with another model →Estimate monthly cost →
INPUT
$0.000/M
per million input tokens
OUTPUT
$0.000/M
per million output tokens
BLENDED 70/30
$0.000/M
default reference rate · how it's calculated →
CONTEXT
131K
131,072 tokens
What it's good at
  • Persona/tuning beyond the base model
  • Persona/style adherence beyond the base model
  • Specific domain (RP, instruction, etc.) tuning
  • Inherits base-model capability
Typical use cases
  • Roleplay and creative chat
  • Domain-specific assistants
  • Custom persona deployments
Benchmarks
No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.
More from nousresearch
See all 4 →
Nous: Hermes 4 70B
text->text · 131K ctx
in $0.130/Mout $0.400/M
Nous: Hermes 4 405B
text->text · 131K ctx
in $1.000/Mout $3.000/M
Nous: Hermes 3 70B Instruct
text->text · 131K ctx
in $0.700/Mout $0.700/M
Nous: Hermes 3 405B Instruct
text->text · 131K ctx
in $1.000/Mout $1.000/M
Frequently asked questions

How much does Nous: Hermes 3 405B Instruct (free) cost?

Nous: Hermes 3 405B Instruct (free) costs $0.000 per million input tokens and $0.000 per million output tokens, for a blended reference rate of $0.000 per million tokens.

What is Nous: Hermes 3 405B Instruct (free)'s context window?

Nous: Hermes 3 405B Instruct (free) supports up to 131K tokens of context (131,072 tokens).

What is Nous: Hermes 3 405B Instruct (free) best for?

Nous: Hermes 3 405B Instruct (free) is well suited to Persona/tuning beyond the base model, Persona/style adherence beyond the base model and Specific domain (RP, instruction, etc.) tuning.

Who makes Nous: Hermes 3 405B Instruct (free)?

Nous: Hermes 3 405B Instruct (free) is developed and served by nousresearch.