Wszystkie modelechatMuse Spark 1.3

Muse Spark 1.3

od MetaPremium

Wypróbuj na Kunya
chat

Muse Spark 1.3

Meta multimodal reasoning model for long-running agentic, multi-agent, and coding workflows — text, image, video, PDF, and audio input with 1M context, tool calling, structured output, and configurable reasoning. Available globally on OpenRouter (unlike Muse Spark 1.1). Audio understanding is still limited upstream.

ID modelu:muse-spark-1.3

Dokumentacja API

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Treść żądania
{
  "model": "muse-spark-1.3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true
}
Przykład cURL
curl -X POST https://kunya.ai/api/v1/chat/completions \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"muse-spark-1.3","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true}'

Uwagi

  • •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.

Ceny

Wejście$1.625 za 1M tokenów
Wyjście$5.525 za 1M tokenów
Okno kontekstu1049K

Kunya benchmark

Updated 2026-10-06 · #3 performance · #13 value

Performance
97.0
Value (KVI)
77.2
Literary writing
82.8
SWE Verified
86.6%
Cost
$6.80/1k tasks
Full benchmark report →

Możliwości

Streaming Tak
Wizja Tak
Rozumowanie Tak
Narzędzia Tak
DostawcaMeta
Wypróbuj na Kunya

Podobne modele

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.

Dokumentacja API

MiMo v2.5

Xiaomi

Native omnimodal model — Pro-level agentic performance at half the cost, with image & video understanding and 1M context

Dokumentacja API

Gemini 3.1 Pro

Google

Most advanced reasoning model with complex problem-solving

Dokumentacja API

Claude Sonnet 4.5

Anthropic

Previous smart model for complex agents and coding

Dokumentacja API