Request Generation Details API

The Request Generations Details API delivers comprehensive analytics—including usage, cost, model/provider details, and performance data—for any previous generation request.

Request Generations Details API

The Request Generations Details API lets you retrieve detailed usage and performance metrics for a previously executed generation request using its generation_id.

This API is especially useful for:

• Cost tracking (credits, tokens, provider-level billing)

• Debugging model behavior

• Auditing model usage in multi-team setups

• BYOK (Bring Your Own Key) visibility

• Performance analysis (latency, token throughput)

---

Endpoint

POST https://go.fastrouter.ai/api/v1/generation

---

Use Cases

• Track cost per request

• View model + provider used

• Inspect input/output token usage

• See whether a request used BYOK

• Analyze latency & performance

---

Request Format (cURL)

curl --location --request POST 'https://go.fastrouter.ai/api/v1/generation' \
--header 'Authorization: Bearer API-KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
  "generation_id": "GEN-ID"
}'

---

Response Format

{
    "id": "GEN-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
}

---