Claude Opus 5
claude-opus-5Claude Opus 5 is Anthropic's current flagship Opus — near-Fable intelligence at half Fable's token price.
Overview
Auth: Authorization: Bearer sk-… from the Console. Use this model id exactly in the model field.
Streaming (optional)
POST /v1/chat/completions with "stream": true. Response Content-Type is text/event-stream.
First line: retry: 3000 (reconnect delay ms). Each chunk: id: N then data: {JSON}. Heartbeats: : PING comment lines (~every 30s). End: data: [DONE].
Use the "id" field inside the first data JSON (e.g. chatcmpl-abc…) as stream_id for resume.
GET /v1/chat/completions/stream/resume/{stream_id}?last_event_id=N with the same Bearer key. Also accepts Last-Event-ID header. Replays cached chunks from N+1; waits for new chunks if still generating.
Hub expired (>30 min after completion) or server restarted. Do not retry resume — re-submit POST or fetch final result another way.
Video models use async POST/GET polling, not SSE. See Video Integration section.
Errors
- 401 — invalid or missing Bearer key
- 402 — insufficient wallet balance (top up in Account)
- 403 — model id not on the whitelist / wrong id spelling
- 429 — rate limited; back off and retry
- 502 — temporary gateway error; retry
FAQ — API parameters & pricing
claude-opus-5 — official vs LumeAPI pricing
Official: $5.00 / $25.00. LumeAPI: $2.50 / $12.50 (per 1M input/output tokens). /models/claude-opus-5
How to call claude-opus-5 with openai compatible api
POST https://api.lumeapi.site/v1/chat/completions, model="claude-opus-5", Bearer key. Same shape as OpenAI Chat Completions — /openai-compatible-api.
Claude Opus 5 API docs and curl
/docs/models/claude-opus-5 · cross-provider pricing: /ai-api-pricing
openai sdk compatible — claude-opus-5 base_url
base_url=https://api.lumeapi.site/v1, model="claude-opus-5". Do not append /chat/completions in SDK clients.
Related guides
- AI agent API bills out of controldoc/21 page batch · 22 impressions
- openai compatible api11 GSC impressions · change base URL, keep SDK
- OpenRouter too expensivedoc/21 page batch · 11 impressions
- llm api gatewayGSC page 5 impressions · gateway vs multi-model
- claude api alternativeGSC page 4 impressions · rank 10
- OpenAI & Claude API pricingCross-provider GPT / Claude / Gemini pricing table
- cheapest llm api/low-cost-llm-api 301s here
- openai api alternativeGPT + Claude + Gemini on one client