Generations

Get Generation Details

post

Retrieves detailed usage and performance metrics for a past generation request. Returns cost breakdown, model/provider info, token counts, latency, throughput, and BYOK status.

Authorizations

AuthorizationstringRequired

FastRouter API Key. Get yours at https://fastrouter.ai

Format: Authorization: Bearer YOUR_API_KEY

Body

generation_idstringRequired

The generation ID returned in the API response. Can be chat_id, request_id, or similar ID field from any FastRouter API endpoint response.

Example: transaction_id

Responses

200

Generation details retrieved successfully

application/json

idstringOptional

Generation ID (same as requested)

Example: transaction_id

modelstringOptional

Model used for this generation in provider/model format

Example: openai/gpt-3.5-turbo

provider_namestringOptional

Provider that processed the request

Example: openai

api_keystringOptional

Hashed API key used for the request (for auditing)

Example: API-KEY-HASH

credits_usednumberOptional

Total credits consumed by this request

Example: 0.000609

query_timestring · date-timeOptional

ISO 8601 timestamp of when the request was made

Example: 2025-05-06T13:51:02.889Z

avg_response_time_minutes_per_transactionnumberOptional

Average response time in minutes per transaction

Example: 0.03524546428333333

avg_tokens_per_nanonumberOptional

Average tokens processed per nanosecond (throughput metric)

Example: 1.5866666666666667

input_token_sizeintegerOptional

Number of tokens in the input/prompt

Example: 14

output_token_sizeintegerOptional

Number of tokens in the generated output/completion

Example: 105

is_byokbooleanOptional

Whether this request used Bring Your Own Key (BYOK). True if customer's own API key was used.

Example: false

endpointstringOptional

API endpoint used for the request

Example: /v1/chat/completions

created_atintegerOptional

Unix timestamp of request creation

requestobjectOptional

Full request body that was sent (if available)

responseobjectOptional

Full response body that was returned (if available)

metadataobjectOptional

Additional metadata about the request

400

Bad Request - Invalid generation ID format

401

Invalid Credentials - Your API key is invalid, missing, or disabled. Check your credentials.

Note: the 401 error body uses code, message, param, and type (there is no status field), and type is invalid_request_error.

application/json

404

Not Found - Generation ID not found or expired

429

Rate Limited - You have exceeded your request limits (TPM/RPM). Slow down or increase your limits.

application/json

500

Internal Server Error

post/api/v1/generation

POST /api/v1/generation HTTP/1.1
Host: api.fastrouter.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 34

{
  "generation_id": "transaction_id"
}

{
  "id": "transaction_id",
  "model": "openai/gpt-3.5-turbo",
  "provider_name": "openai",
  "api_key": "API-KEY-HASH",
  "credits_used": 0.000609,
  "query_time": "2025-05-06T13:51:02.889Z",
  "avg_response_time_minutes_per_transaction": 0.03524546428333333,
  "avg_tokens_per_nano": 1.5866666666666667,
  "input_token_size": 14,
  "output_token_size": 105,
  "is_byok": false
}