Skip to main content
The TypeScript SDK and docs are currently in beta. Report issues on GitHub.
Streaming chat completion chunk

​
Example Usage

import { ChatStreamChunk } from "@openrouter/sdk/models";

let value: ChatStreamChunk = {
  choices: [
    {
      delta: {},
      finishReason: null,
      index: 0,
    },
  ],
  created: 1677652288,
  id: "chatcmpl-123",
  model: "openai/gpt-4",
  object: "chat.completion.chunk",
};

​
Fields

FieldTypeRequiredDescriptionExample
choicesmodels.ChatStreamChoice[]:heavy_check_mark:List of streaming chunk choices
creatednumber:heavy_check_mark:Unix timestamp of creation1677652288
errormodels.ErrorT:heavy_minus_sign:Error information{"code": 429,"message": "Rate limit exceeded"}
idstring:heavy_check_mark:Unique chunk identifierchatcmpl-123
modelstring:heavy_check_mark:Model used for completionopenai/gpt-4
objectmodels.ChatStreamChunkObject:heavy_check_mark:N/A
openrouterMetadatamodels.OpenRouterMetadata:heavy_minus_sign: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”
}
serviceTierstring:heavy_minus_sign:The service tier used by the upstream provider for this requestdefault
systemFingerprintstring:heavy_minus_sign:System fingerprintfp_44709d6fcb
usagemodels.ChatUsage:heavy_minus_sign: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/>}