Alla modellerchatClaude Sonnet 5.5

Claude Sonnet 5.5

av AnthropicPremium

Testa på Kunya
chat

Claude Sonnet 5.5

Latest Sonnet — 30%+ faster with stronger coding and agentic performance at the same list price as Sonnet 5

Modell-ID:claude-sonnet-5-5

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "claude-sonnet-5-5",
  "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":"claude-sonnet-5-5","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$2.6 per 1M tokens
Utdata$13 per 1M tokens
Kontextfönster1000K

Kunya benchmark

Updated 2026-10-06 · #18 performance · #14 value

Performance
93.3
Value (KVI)
75.8
Literary writing
98.5
Hard tier
75.2
SWE Verified
79.6%
Cost
$3.53/1k tasks
Full benchmark report →

Funktioner

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

Rankningar

Overall#1
Programming#1

Liknande modeller

Claude Sonnet 4.6

Anthropic

Previous Sonnet — strong speed and intelligence balance

API-dokumentation

Claude Opus 4.7

Anthropic

Previous Opus — enhanced SWE, vision, and long-horizon agentic reasoning with 1M context

API-dokumentation

Gemini 2.5 Pro

Google

State-of-the-art thinking model for complex problems

API-dokumentation

Kimi K2.7 Code

Moonshot

Coding-focused MoE model for long-horizon programming, agentic task decomposition, and multimodal reasoning

API-dokumentation