Claude Fable 5 is Anthropic’s advanced long-horizon reasoning model, supporting text, image, and file inputs with text output. It features reasoning capabilities and a 1M-token context window, making it suitable for autonomous knowledge work, software development, and complex multi-step tasks.
| 規格 | 價格 |
|---|---|
| 輸入 | $10/ M tokens |
| 輸出 | $50/ M tokens |
| 快取讀 | $1/ M tokens |
| 快取寫 | $12.5/ M tokens |
| 快取寫 1h | $20/ M tokens |
可直接貼上執行下方範例程式碼。Gate.AI API 與 OpenAI 相容，多數 SDK 只需替換 base URL；切換模型時，只需修改模型 ID。
Sign in to the Gate.AI console and create a new key under "API Keys". Keep it safe and send it via the Authorization header on every request.
前往控制台建立金鑰Send a POST request to the Chat Completions endpoint with a model ID and an array of messages to get a reply.
curl --location "https://api.gate.ai/anthropic/v1/messages" \
--header "x-api-key: {API_KEY}" \
--header "anthropic-version: 2023-06-01" \
--header "Content-Type: application/json" \
--data '{
"model": "claude-fable-5",
"max_tokens": 256,
"messages": [
{"role": "user", "content": "Hello"}
]
}'By default a full JSON response is returned. Add "stream": true to the request body to receive incremental chunks over SSE.
curl --no-buffer --location "https://api.gate.ai/anthropic/v1/messages" \
--header "x-api-key: {API_KEY}" \
--header "anthropic-version: 2023-06-01" \
--header "Content-Type: application/json" \
--data '{
"model": "claude-fable-5",
"max_tokens": 256,
"messages": [
{"role": "user", "content": "Hello"}
],
"stream": true
}'以 Anthropic Messages API 格式建立訊息，支援文字、圖片、工具與延伸思考。
基礎 URL、請求方法與必要請求頭，皆依當前模型的協議模板渲染。
Claude Haiku 5.5Small, fast model for high-volume, latency-sensitive summarization, subagents, and browser use, with stronger coding and computer use than the prior generation.
Claude Sonnet 5.5Sonnet-class model for well-scoped everyday work, with stronger feature building, bug fixing, and office deliverables than the prior generation, suited to responsive agentic loops.
Claude Opus 5.5Successor to Opus 5 for demanding reasoning, coding, and long-horizon agent work; excels at multi-step changes across large codebases and sustained knowledge tasks.
Claude Opus 5Flagship model for demanding reasoning, coding, and long-horizon agentic work, spanning end-to-end software, code review, parallel subagent coordination, visual analysis of charts and documents, and complex office deliverables.
Claude Sonnet 5Coding and agent quality approach the frontier, with native reasoning built in, well-suited for complex planning and long-horizon professional tasks that require cross-step consistency.
Claude Opus 4.8Opus family flagship with reasoning. Suited for long-horizon autonomous agents, large-codebase analysis, and multimodal knowledge work.
Claude Opus 4.8 betaOpus family flagship with reasoning. Suited for long-horizon autonomous agents, large-codebase analysis, and multimodal knowledge work.
Claude Opus 4.7 betaBuilt for long-running async agents, excelling at complex multi-step tasks and end-to-end workflow execution.
Claude Opus 4.7Built for long-running async agents, excelling at complex multi-step tasks and end-to-end workflow execution.
Claude Sonnet 4.6Anthropic 品質與成本的最佳平衡。