ChatStreamChunk Type | OpenRouter TypeScript SDK | OpenRouter

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

Streaming chat completion chunk

Example Usage

1 import { ChatStreamChunk } from "@openrouter/sdk/models";
2 
3 let value: ChatStreamChunk = {
4   choices: [
5     {
6       delta: {},
7       finishReason: null,
8       index: 0,
9     },
10   ],
11   created: 1677652288,
12   id: "chatcmpl-123",
13   model: "openai/gpt-4",
14   object: "chat.completion.chunk",
15 };

Fields

Field	Type	Required	Description	Example
`choices`	models.ChatStreamChoice[]	✔️	List of streaming chunk choices
`created`	number	✔️	Unix timestamp of creation	1677652288
`error`	models.ErrorT	➖	Error information	`{"code": 429,"message": "Rate limit exceeded"}`
`id`	string	✔️	Unique chunk identifier	chatcmpl-123
`model`	string	✔️	Model used for completion	openai/gpt-4
`object`	models.ChatStreamChunkObject	✔️	N/A
`openrouterMetadata`	models.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” }
`serviceTier`	string	➖	The service tier used by the upstream provider for this request	default
`systemFingerprint`	string	➖	System fingerprint	fp_44709d6fcb
`usage`	models.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 />`}