Files
openrouter-python-sdk-retry…/docs/components/chatstreamingresponsechunk.md
T
OpenRouter Team ca36f2362c Commits included in this export:
- bb413e979a46ef67c2f266743f7ebd798af42afb
  - b60e92d5dcec83f31986164f51c010d1728b2b17
  - 45687f423707f5838461585c568a024a19eb2f06
  - 3103d3ca68b6e42ccdb6136588ec2b6edc8dcab0
  - fd9f991606027cd86116317c71f8eb7b4e2aa3eb
  - 0f312019161edd76c1e5923d142c788d22f096d5
  - 5dbab2094bc744db4a90b3097520d897e5d0d634
  - 4c47d1af1735db18a1c1a7f463e801c7f71ad4e5

GitOrigin-RevId: bb413e979a46ef67c2f266743f7ebd798af42afb
2026-02-20 19:18:17 +00:00

8.7 KiB
Raw Blame History

ChatStreamingResponseChunk

Streaming chat completion chunk

Fields

Field Type Required Description Example
id str ✔️ Unique chunk identifier chatcmpl-123
choices List[components.ChatStreamingChoice] ✔️ List of streaming chunk choices
created float ✔️ Unix timestamp of creation 1677652288
model str ✔️ Model used for completion openai/gpt-4
object components.ChatStreamingResponseChunkObject ✔️ N/A
system_fingerprint OptionalNullable[str] System fingerprint fp_44709d6fcb
error Optional[components.Error] Error information {
"message": "Rate limit exceeded",
"code": 429
}
usage Optional[components.ChatGenerationTokenUsage] Token usage statistics {
"completion_tokens": 15,
"prompt_tokens": 10,
"total_tokens": 25,
"completion_tokens_details": {
"reasoning_tokens": 5
},
"prompt_tokens_details": {
"cached_tokens": 2
}
}