Alla modellerchatMiMo v2.6 Pro

MiMo v2.6 Pro

av XiaomiPremium

Testa på Kunya
X
chat

MiMo v2.6 Pro

1T+ parameter flagship — 1M context, native multimodal, top-tier agentic coding, visual, and research workloads

Modell-ID:mimo-v2.6-pro

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "mimo-v2.6-pro",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true
}
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":"mimo-v2.6-pro","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true}'

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$0.5655 per 1M tokens
Utdata$1.131 per 1M tokens
Kontextfönster1050K

Kunya benchmark

Updated 2026-10-06 · #4 performance · #5 value

Performance
96.7
Value (KVI)
117.1
Literary writing
85.8
SWE Verified
74.0%
Cost
$1.00/1k tasks
Full benchmark report →

Funktioner

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

Rankningar

Programming#2
Technology#3

Liknande modeller

Ox Alpha

Stealth

Reasoning model built for coding, sustained agentic work, and production workloads — 1M context, 131K output, image & video input, tool calling. Free on Kunya until August 27.

API-dokumentation

Kimi K2.5

Moonshot

State-of-the-art visual coding and agentic tool-calling with multimodal reasoning

API-dokumentation

GPT-5.2 Pro

OpenAI

Smarter and more precise responses

API-dokumentation

GPT-5

OpenAI

Previous intelligent reasoning model for coding and agentic tasks

API-dokumentation