Skip to main content
GET
/
generations
Get generation
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.phaseo.app/v1/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
{
  "created_at": "2023-11-07T05:31:56Z",
  "request_id": "<string>",
  "team_id": "<string>",
  "app_id": "<string>",
  "endpoint": "<string>",
  "model_id": "<string>",
  "provider": "<string>",
  "native_response_id": "<string>",
  "stream": true,
  "byok": true,
  "status_code": 123,
  "success": true,
  "error_code": "<string>",
  "error_message": "<string>",
  "latency_ms": 123,
  "generation_ms": 123,
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  },
  "cost_nanos": 123,
  "currency": "<string>",
  "pricing_lines": [
    {}
  ],
  "key_id": "<string>",
  "throughput": 123,
  "replay_supported": true,
  "replay_request": {}
}
Fetches the stored audit record for a given request_id that belongs to your team. Use:
  • GET /v1/generations?id=<request_id>
When the gateway captured full request details for that generation, the response also includes:
  • replay_supported: whether a replay-ready payload is available
  • replay_request: the stored request body you can send back to the original endpoint for a controlled rerun
Typical replay flow:
  1. Read the generation record with GET /v1/generations?id=<request_id>.
  2. Check replay_supported === true.
  3. Re-submit replay_request to the original endpoint named by endpoint such as /v1/chat/completions or /v1/responses.

Authorizations

​
Authorization
string
header
required

Bearer token authentication

Query Parameters

​
id
string
required

The ID of the generation

Response

Generation data

​
created_at
string<date-time>
​
request_id
string
​
team_id
string
​
app_id
string | null
​
endpoint
string
​
model_id
string
​
provider
string
​
native_response_id
string | null
​
stream
boolean
​
byok
boolean
​
status_code
number
​
success
boolean
​
error_code
string | null
​
error_message
string | null
​
latency_ms
number
​
generation_ms
number
​
usage
object
​
cost_nanos
number
​
currency
string
​
pricing_lines
object[]
​
key_id
string
​
throughput
number | null
​
replay_supported
boolean

Whether a replay-ready request payload is available for this generation.

​
replay_request
object

Replay-ready request payload captured for this generation when available.

Last modified on May 6, 2026