Loading the catalogue…
NousResearch
Hermes-4-405B
Released 26 Aug 2025
Nous Research's open-weight 405B hybrid reasoning model based on Llama 3.1, with a 131K-token context and text input and output.
€0.90/€2.69per 1M in / out
Loading the catalogue…
Nous Research's open-weight 405B hybrid reasoning model based on Llama 3.1, with a 131K-token context and text input and output.
| Inference Provider | Sovereignty | Runs in | In / out per 1M | Status | Pin |
|---|---|---|---|---|---|
| L2 | €0.90 / 2.69 | Online |
24 use cases classified by the curator. The note says why.
Tool-calling, extended thinking, and a 131072-token context window directly support iterative coding agents operating across sizeable repositories.
The 405B parameter count, extended-thinking mode, and 131072-token context support evidence-heavy audit analysis across large document sets.
Extended thinking and tool-calling support systematic debugging across logs, code, and diagnostic tools, with ample context for large incidents.
A 405B-parameter model with extended thinking is well suited to nuanced classification tasks involving ambiguous or policy-dependent labels.
The 405B parameter count and extended-thinking capability provide strong capacity for context-sensitive code generation, with tool-calling available for development workflows.
The large context window and extended-thinking capability support explanations spanning modules, dependencies, and complex control flow.
Tool-calling and extended thinking support browser-control workflows, although no browser-specific benchmark or visual capability is documented.
Extended thinking and tool-calling support analytical workflows, although no execution environment or data-analysis benchmark is documented.
Sourced numbers, not our own evaluations. Percentiles are against the whole Stav catalogue.
curl https://api.stav.ai/v1/chat/completions \
-H "Authorization: Bearer $STAV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nousresearch/hermes-4-405b",
"reasoning_effort": "high",
"messages": [{"role": "user", "content": "Hello!"}]
}'→ X-Stav-Request-Id · X-Stav-Model · X-Stav-Provider → X-Stav-Sovereignty-Level — the rung the request was served at