od DeepSeekSzybki
DeepSeek V4.1 Flash 1017
Oct 17, 2026 V4.1 Flash snapshot (CED MoE) — native vision, coding & agentic workloads, 1M context, compressed KV cache
deepseek-v4.1-flash-1017Generate chat completions with this model.
/api/v1/chat/completionsGET /api/v1/models?type=chat{
"model": "deepseek-v4.1-flash-1017",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": false,
"thinking": true,
"max_tokens": 4096
}curl -X POST https://kunya.ai/api/v1/chat/completions \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"deepseek-v4.1-flash-1017","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"max_tokens":4096}'Qwen
First agentic omni-modal Qwen — native audio, image & video input, tool calling, 1M context for multimodal agents
Dokumentacja APIMeta
Cost-efficient contributor tier of Muse Spark 1.3 for experimentation and early-stage agentic workflows — same 1M multimodal context and tool calling at ~20× lower cost. Prompts and outputs may be used to improve Meta products. Available globally on OpenRouter.
Dokumentacja APIStable Flash — strong agentic and multimodal performance with lower output cost than 3.5 Flash
Dokumentacja API