Alla modellerchatDeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017

av DeepSeekSnabb

Testa på Kunya
chat

DeepSeek V4.1 Flash 1017

Oct 17, 2026 V4.1 Flash snapshot (CED MoE) — native vision, coding & agentic workloads, 1M context, compressed KV cache

Modell-ID:deepseek-v4.1-flash-1017

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "deepseek-v4.1-flash-1017",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true,
  "max_tokens": 4096
}
cURL-exempel
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}'

Anteckningar

  • •OpenAI-compatible endpoint — works with any Kunya API key.
  • •Set `"stream": true` for server-sent events.
  • •Supports vision: pass image URLs in message content as `{ "type": "image_url", "image_url": { "url": "..." } }`.
  • •Supports tool calling via the `tools` parameter.

Priser

Indata$0.195 per 1M tokens
Utdata$0.78 per 1M tokens
Kontextfönster1049K

Funktioner

Streaming Ja
Vision Ja
Resonemang Ja
Verktyg Ja
LeverantörDeepSeek
Testa på Kunya

Rankningar

Programming#5
Tool Use#6

Liknande modeller

DeepSeek V4 Flash

DeepSeek

1M context, thinking + non-thinking modes, tool calls

API-dokumentation

Kunya Tab v1

Kunya

Fast Tab completion router — routes to the configured flash model with curation telemetry.

API-dokumentation

MiniMax M3.1 Flash

MiniMax

Latest M-series Flash — 1M context, multimodal (image & video), agentic coding, tunable thinking depth via reasoning_effort

API-dokumentation

GLM 5.3 FlashX

Z-AI

High-speed GLM 5.3 Flash serving tier — up to ~200 tok/s for coding, vision, and agent tasks with 1M context

API-dokumentation