Use case
Claude Opus 4.8 streaming
streaming notes for claude-opus-4-8: the rate card, a worked volume, and when to send this ID. A sample of 1 million input tokens plus 200 thousand output tokens is about $2.00 on corouter (input $1.00, output $1.00).
How streaming is billed
A streamed response is still billed on input and output tokens, not on how long the socket stays open. Output for claude-opus-4-8 is $5.00 per million tokens.
A sample of 1 million input tokens plus 200 thousand output tokens is about $2.00 on corouter (input $1.00, output $1.00).
A field you can set
A familiar chat-completions shape often sets "stream": true next to "model": "claude-opus-4-8". On a messages shape, follow the stream field your client actually sends.
Claude Opus 4.8 matches the Opus 5 list rate and window, without the Opus 5.5 cache-read cut. Send claude-opus-4-8 to keep an Opus 4.8 client unchanged.
Questions
- Which model ID should the request send?
- Send claude-opus-4-8. Do not put a different name in the model field.
- What is the minimum top-up?
- Prepaid credits, $5 minimum top-up, no subscription tier.