ChatStreamChunk | OpenRouter Python SDK | OpenRouter

The Python SDK and docs are currently in beta. Report issues on GitHub.

Streaming chat completion chunk

Fields

Field	Type	Required	Description	Example
`choices`	List[components.ChatStreamChoice]	✔️	List of streaming chunk choices
`created`	int	✔️	Unix timestamp of creation	1677652288
`error`	Optional[components.Error]	➖	Error information	`{"code": 429,"message": "Rate limit exceeded"}`
`id`	str	✔️	Unique chunk identifier	chatcmpl-123
`model`	str	✔️	Model used for completion	openai/gpt-4
`object`	components.ChatStreamChunkObject	✔️	N/A
`openrouter_metadata`	Optional[components.OpenRouterMetadata]	➖	N/A	`{"attempt": 1,"endpoints": {"available": [{"model": "openai/gpt-4o","provider": "OpenAI","selected": true}` ], “total”: `1<br />`}, “is_byok”: false, “region”: “iad”, “requested”: “openai/gpt-4o”, “strategy”: “direct”, “summary”: “available=1, selected=OpenAI” }
`service_tier`	OptionalNullable[str]	➖	The service tier used by the upstream provider for this request	default
`system_fingerprint`	Optional[str]	➖	System fingerprint	fp_44709d6fcb
`usage`	Optional[components.ChatUsage]	➖	Token usage statistics	`{"completion_tokens": 15,"completion_tokens_details": {"reasoning_tokens": 5}`, “cost”: 0.0012, “cost_details”: `{"upstream_inference_completions_cost": 0.0004,"upstream_inference_cost": null,"upstream_inference_prompt_cost": 0.0008}`, “is_byok”: false, “prompt_tokens”: 10, “prompt_tokens_details”: `{"cached_tokens": 2}`, “total_tokens”: `25<br />`}