Laster katalogen …
Laster katalogen …
Nous Research's open-weight 405B hybrid reasoning model based on Llama 3.1, with a 131K-token context and text input and output.
| Inferensleverandør | Suverenitet | Kjører i | Inn / ut per 1M | Status | Lås |
|---|---|---|---|---|---|
| L2 | 0,91 / 2,72€ | Tilkoblet |
24 bruksområder klassifisert av kuratoren. Notatet forklarer hvorfor.
Tool-calling, extended thinking, and a 131072-token context window directly support iterative coding agents operating across sizeable repositories.
Native tool-calling support directly matches function-calling application workflows, while the large model size supports complex argument selection and task logic.
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 large context window and extended-thinking capability support explanations spanning modules, dependencies, and complex control flow.
The 405B parameter count and extended-thinking capability provide strong capacity for context-sensitive code generation, with tool-calling available for development workflows.
Extended thinking and tool-calling support analytical workflows, although no execution environment or data-analysis benchmark is documented.
Tool-calling and extended thinking support browser-control workflows, although no browser-specific benchmark or visual capability is documented.
Innhentede tall, ikke våre egne evalueringer. Persentilene er mot hele Stav-katalogen.
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 – nivået forespørselen ble betjent på