Laster katalogen …
Qwen's open-weight multimodal MoE model with 397B total and 17B active parameters, image input and a 262,144-token context.
| Inferensleverandør | Suverenitet | Kjører i | Inn / ut per 1M | Status | Lås |
|---|---|---|---|---|---|
| L3 | 0,60 / 3,60€ | Tilkoblet | |||
| L1 | 0,60 / 3,60€ | Tilkoblet | |||
| L1 | 0,60 / 3,60€ | Tilkoblet | |||
| L0 | 0,41 / 2,72€ | Tilkoblet |
16 bruksområder klassifisert av kuratoren. Notatet forklarer hvorfor.
Tool-calling, extended thinking, and a 262K context make it well suited to agent loops that read, edit, and test large codebases, though no coding benchmark is curated yet.
Tool-calling capability combined with extended thinking gives reliable argument selection and call sequencing for function-calling applications.
The 262K context window can hold large diffs or multi-file repositories in one pass, and extended thinking supports reasoning over changes.
Vision input paired with tool-calling supports the screenshot-observe-act loop that browser agents depend on.
Extended-thinking mode plus a 262K context supports decomposing long, multi-stage tasks and tracking state across steps.
Very large context plus extended thinking suits synthesising across many long sources in a single reasoning pass.
Vision input can read document pages, but no OCR-specific benchmark is curated and dedicated OCR models are typically cheaper per page.
Vision capability supports chart reading and narration; the fit is inferred from general multimodal support rather than chart-specific evidence.
Vision input is supported, but no UI-grounding or screenshot benchmark is curated, so the fit is inferred from general vision capability.
The 262K context handles long inputs well, but at 397B total parameters the cost and latency profile is heavier than smaller summarisation options.
No audio output capability is listed; speech synthesis requires a dedicated TTS model.
No audio input is listed among the capabilities (tool-calling, vision, extended thinking), so the model cannot handle transcription directly.
Innhentede tall, ikke våre egne evalueringer. Persentilene er mot hele Stav-katalogen.
Beregnet fra aa-intelligence-index, gpqa-diamond, aa-engineering-index, aa-coding-index, livecodebench, terminal-bench-v4, ifbench, aa-multilingual-index, aa-lcr.
curl https://api.stav.ai/v1/chat/completions \
-H "Authorization: Bearer $STAV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-5-397b-a17b",
"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