Indlæser kataloget…
Open-weight Qwen MoE model with text and image input, configurable reasoning, about 6B active parameters and a 262,144-token context.
| Inferensleverandør | Suverænitet | Kører i | Ind / ud per 1 mio. | Status | Fastgør |
|---|---|---|---|---|---|
| L1 | 0,18 / 0,45€ | Online |
31 anvendelsesområder klassificeret af redaktøren. Noten forklarer hvorfor.
Tool-calling, extended thinking, and 262K context directly support iterative coding agents operating over substantial repositories.
Native tool-calling support directly matches function-calling application patterns, with 262K context for larger state and instruction histories.
Tool-calling and vision support fit browser interaction workflows, while extended thinking supports multi-step page-state reasoning.
Extended thinking supports tracing multi-file failure causes, while 262K context accommodates substantial logs and code context.
Vision capability supports chart interpretation, and extended thinking can connect visual trends with accompanying context.
Vision support directly matches screenshot understanding, and extended thinking helps interpret UI state and multi-element layouts.
Tool-calling enables integrations and extended thinking supports complex support cases; the 262K context is useful for conversation and knowledge-base state.
Extended thinking and tool-calling support analytical workflows and external computation, but no data-analysis benchmark or execution environment is documented.
Vision capability supports document image interpretation, but dedicated OCR accuracy or document-parsing benchmarks are not provided.
The model’s reasoning capability and large context support nuanced classification tasks, but there is no classification-specific benchmark in the profile.
The family is positioned for reasoning-heavy workloads and the model has extended thinking, but no code benchmark or coding-specific score is provided for this variant.
The large context window supports long-document translation, but the profile provides no translation-specific benchmark or language coverage evidence.
Tal fra eksterne kilder, ikke vores egne vurderinger. Percentiler er målt mod hele Stav-kataloget.
Beregnet ud fra aa-intelligence-index, gpqa-diamond, aa-engineering-index, aa-coding-index, livecodebench, terminal-bench-v4, aa-lcr.
curl https://api.stav.ai/v1/chat/completions \
-H "Authorization: Bearer $STAV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-8-flash-next",
"messages": [{"role": "user", "content": "Hello!"}]
}'→ X-Stav-Request-Id · X-Stav-Model · X-Stav-Provider → X-Stav-Sovereignty-Level — det niveau, forespørgslen blev betjent på