Hermes 4 405B
Nous Research · Open weights · Released Aug 26, 2025 · nousresearch/hermes-4-405b
131K contextReasoningStructured outputOpen weights
Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $1.00 | $3.00 | — | 131K | fp8 | 1.8s | 29 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
About
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...
Specifications
Context window131,072
Max output—
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedAug 26, 2025
Knowledge cutoff2024-08-31
TokenizerOther
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/nousresearch/hermes-4-405b)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks44 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.