Alla modellerchatKunya V1

Kunya V1

av KunyaPremium

Testa på Kunya
Kunya
chat

Kunya V1

Intelligently routed model — Opus-level quality at budget cost. Routes to the best model for each request.

Modell-ID:kunyav1

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "kunyav1",
  "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":"kunyav1","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 per 1M tokens
Utdata$0 per 1M tokens
Kontextfönster1000K

Kunya benchmark

Updated 2026-10-06 · #1 performance · #10 value

Performance
97.8
Value (KVI)
165.3
Literary writing
92.5
Hard tier
76.8
Cost
$0.23/1k tasks
Full benchmark report →

Funktioner

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

Liknande modeller

GPT-5.6 Terra

OpenAI

GPT-5.6 agentic execution — prefer GPT-6.1 Terra for new agent and tool workflows

API-dokumentation

GPT-6 Sol

OpenAI

Cost-efficient GPT-6 high-end model — prefer GPT-6.1 Sol for agentic coding and long-horizon software engineering

API-dokumentation

Muse Spark 1.3

Meta

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.

API-dokumentation

Seed 2.0 Pro

ByteDance

ByteDance flagship — 76.5% SWE-Bench, 98.3% AIME 2025, hour-long video understanding

API-dokumentation