mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
21 lines
26 KiB
Plaintext
21 lines
26 KiB
Plaintext
---
|
|
title: "ChatStreamChunk"
|
|
---
|
|
|
|
Streaming chat completion chunk
|
|
|
|
|
|
## Fields
|
|
|
|
| Field | Type | Required | Description | Example |
|
|
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `choices` | List[[components.ChatStreamChoice](../components/chatstreamchoice.mdx)] | :heavy_check_mark: | List of streaming chunk choices | |
|
|
| `created` | *int* | :heavy_check_mark: | Unix timestamp of creation | 1677652288 |
|
|
| `error` | [Optional[components.ChatStreamChunkError]](../components/chatstreamchunkerror.mdx) | :heavy_minus_sign: | Error information | \{<br/>"code": 429,<br/>"message": "Rate limit exceeded",<br/>"metadata": \{<br/>"error_type": "rate_limit_exceeded"<br/>}<br/>} |
|
|
| `id` | *str* | :heavy_check_mark: | Unique chunk identifier | chatcmpl-123 |
|
|
| `model` | *str* | :heavy_check_mark: | Model used for completion | openai/gpt-4 |
|
|
| `object` | [components.ChatStreamChunkObject](../components/chatstreamchunkobject.mdx) | :heavy_check_mark: | N/A | |
|
|
| `openrouter_metadata` | [Optional[components.OpenRouterMetadata]](../components/openroutermetadata.mdx) | :heavy_minus_sign: | N/A | \{<br/>"attempt": 1,<br/>"endpoints": \{<br/>"available": [<br/>\{<br/>"model": "openai/gpt-4o",<br/>"provider": "OpenAI",<br/>"selected": true<br/>}<br/>],<br/>"total": 1<br/>},<br/>"is_byok": false,<br/>"region": "iad",<br/>"requested": "openai/gpt-4o",<br/>"strategy": "direct",<br/>"summary": "available=1, selected=OpenAI"<br/>} |
|
|
| `service_tier` | *OptionalNullable[str]* | :heavy_minus_sign: | The service tier used by the upstream provider for this request | default |
|
|
| `system_fingerprint` | *Optional[str]* | :heavy_minus_sign: | System fingerprint | fp_44709d6fcb |
|
|
| `usage` | [Optional[components.ChatUsage]](../components/chatusage.mdx) | :heavy_minus_sign: | Token usage statistics | \{<br/>"completion_tokens": 15,<br/>"completion_tokens_details": \{<br/>"reasoning_tokens": 5<br/>},<br/>"cost": 0.0012,<br/>"cost_details": \{<br/>"upstream_inference_completions_cost": 0.0004,<br/>"upstream_inference_cost": null,<br/>"upstream_inference_prompt_cost": 0.0008<br/>},<br/>"is_byok": false,<br/>"prompt_tokens": 10,<br/>"prompt_tokens_details": \{<br/>"cached_tokens": 2<br/>},<br/>"server_tool_use_details": \{<br/>"tool_calls_executed": 2,<br/>"tool_calls_requested": 2<br/>},<br/>"total_tokens": 25<br/>} | |