Wszystkie modelechatClaude Opus 5.5

Claude Opus 5.5

od AnthropicPremium

Wypróbuj na Kunya
chat

Claude Opus 5.5

Anthropic flagship Opus via OpenRouter — multi-step codebase work, code review, and long-horizon agentic tasks

ID modelu:claude-opus-5-5-or

Dokumentacja API

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Treść żądania
{
  "model": "claude-opus-5-5-or",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true,
  "max_tokens": 4096
}
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":"claude-opus-5-5-or","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"max_tokens":4096}'

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$5.2 za 1M tokenów
Wyjście$26 za 1M tokenów
Okno kontekstu1000K

Możliwości

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

Rankingi

Programming#1
Technology#1

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

Qwen 3.8 Max

Qwen

Alibaba's most capable model — 2.4T MoE (95B active), 1M context, vision, agentic coding, office productivity, and long-horizon autonomous execution

Dokumentacja API

Gemini 4 Argon

Google

Google DeepMind frontier — long-horizon software engineering, enterprise knowledge work, and agentic workflows (intro $2/$10 per 1M tokens through Nov 2026)

Dokumentacja API

Grok 4.3

xAI

Fast, intelligent Grok — 1M context, 3 reasoning levels, top agentic tool calling

Dokumentacja API