​
Completions Response Format

BLACKBOXAI uses OpenRouter under the hood and it normalizes the schema across models and providers to comply with the OpenAI Chat API. This means that choices is always an array, even if the model only returns one completion. Each choice will contain a delta property if a stream was requested and a message property otherwise. This makes it easier to use the same code for all models. Here’s the response schema as a TypeScript type:
TypeScript
// Definitions of subtypes are below
type Response = {
  id: string;
  // Depending on whether you set "stream" to "true" and
  // whether you passed in "messages" or a "prompt", you
  // will get a different output shape
  choices: (NonStreamingChoice | StreamingChoice | NonChatChoice)[];
  created: number; // Unix timestamp
  model: string;
  object: 'chat.completion' | 'chat.completion.chunk';

  system_fingerprint?: string; // Only present if the provider supports it

  // Usage data is always returned for non-streaming.
  // When streaming, you will get one usage object at
  // the end accompanied by an empty choices array.
  usage?: ResponseUsage;
};

// If the provider returns usage, we pass it down
// as-is. Otherwise, we count using the GPT-4 tokenizer.

type ResponseUsage = {
  /** Including images and tools if any */
  prompt_tokens: number;
  /** The tokens generated */
  completion_tokens: number;
  /** Sum of the above two fields */
  total_tokens: number;
};

// Subtypes:
type NonChatChoice = {
  finish_reason: string | null;
  text: string;
  error?: ErrorResponse;
};

type NonStreamingChoice = {
  finish_reason: string | null;
  native_finish_reason: string | null;
  message: {
    content: string | null;
    role: string;
    tool_calls?: ToolCall[];
  };
  error?: ErrorResponse;
};

type StreamingChoice = {
  finish_reason: string | null;
  native_finish_reason: string | null;
  delta: {
    content: string | null;
    role?: string;
    tool_calls?: ToolCall[];
  };
  error?: ErrorResponse;
};

type ErrorResponse = {
  code: number; // See "Error Handling" section
  message: string;
  metadata?: Record<string, unknown>; // Contains additional error information such as provider details, the raw error message, etc.
};

type ToolCall = {
  id: string;
  type: 'function';
  function: FunctionCall;
};
Here’s an example: 
{
  "id":"gen-xxxxxxxxxxxxxx",
  "created":1757140020,
  "model":"openai/gpt-4",
  "object":"chat.completion",
  "system_fingerprint":"None",
  "choices":[
    {
      "finish_reason":"stop", // Normalized finish_reason
      "index":0,
      "message":{
        // will be "delta" if streaming
        "content":"The capital of France is Paris.",
        "role":"assistant",
        "tool_calls":"None",
        "function_call":"None"
      },
      "provider_specific_fields":{
        "native_finish_reason":"stop" // The raw finish_reason from the provider
      }
    }
  ],
  "usage":{
    "completion_tokens":7,
    "prompt_tokens":14,
    "total_tokens":21,
    "completion_tokens_details":{
      "accepted_prediction_tokens":"None",
      "audio_tokens":"None",
      "reasoning_tokens":0,
      "rejected_prediction_tokens":"None"
    },
    "prompt_tokens_details":{
      "audio_tokens":0,
      "cached_tokens":0
    }
  },
  "provider":"OpenAI"
}

​
Finish Reason

OpenRouter normalizes each model’s finish_reason to one of the following values: tool_calls, stop, length, content_filter, error. Some models and providers may have additional finish reasons. The raw finish_reason string returned by the model is available via the native_finish_reason property.