Generation lookup

Pass a request ID (such as G-01ABC...) to the SDK’s generation method to fetch the stored record for that request from GET /v1/generations?id=<id>.

const record = await client.getGeneration("G-01ABC...");

record = client.get_generation("G-01ABC...")

print(record["model_id"], record["cost_nanos"])

client, err := phaseo.NewFromEnv()
if err != nil {
  panic(err)
}

record, err := client.GetGeneration(context.Background(), "G-01ABC...")
if err != nil {
  panic(err)
}
fmt.Println(record["status_code"], record["cost_nanos"])

using PhaseoSdk;

var client = new Phaseo();
var record = await client.GetGeneration("G-01ABC...");

<?php
require 'vendor/autoload.php';

use Phaseo\Sdk\Phaseo;

$client = new Phaseo();
$record = $client->getGeneration('G-01ABC...');

require 'phaseo_sdk'

client = PhaseoSdk::Phaseo.new
record = client.get_generation('G-01ABC...')

import app.phaseo.sdk.Phaseo;

Phaseo client = new Phaseo(System.getenv("PHASEO_API_KEY"));

var record = client.getGeneration("G-01ABC...");
System.out.println(record);

Language	Method	Returns
TypeScript	`client.getGeneration(id)`	The record object
Python	`client.get_generation(id)`	`APIResponse` dict
Go	`client.GetGeneration(ctx, id)`	`map[string]interface{}`
C#	`client.GetGeneration(id)`	`Dictionary<string, object>?`
PHP	`$client->getGeneration($id)`	Array
Ruby	`client.get_generation(id)`	Hash
Java	`client.getGeneration(id)`	Jackson `JsonNode`
Rust	No helper; call `client.request("GET", "/generations?id=<id>", None, &RequestOptions::default())`	`PhaseoResponse`, with the record in `body` (a `serde_json::Value`)

The lookup is scoped to your workspace. A missing id returns 400 (missing_id), and an ID that isn’t in your workspace returns 404 (not_found).

Replay a stored request

If the gateway stored the full request, the record has replay_supported set to true and a replay_request, which you can send back to the original endpoint for a controlled rerun.

Read the timing fields

latency_ms: time to the first token, or the first output byte or frame, when tracked.
generation_ms: generation time after that point, when tracked.

Response

{
  "created_at": "2026-05-05T12:00:00.000Z",
  "request_id": "G-01ABC123",
  "team_id": "team-123",
  "app_id": "app-123",
  "endpoint": "chat/completions",
  "model_id": "openai/gpt-6-astra",
  "provider": "openai",
  "native_response_id": "chatcmpl-123",
  "stream": false,
  "byok": false,
  "status_code": 200,
  "success": true,
  "error_code": null,
  "error_message": null,
  "latency_ms": 1500,
  "generation_ms": 1400,
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 9,
    "total_tokens": 18
  },
  "cost_nanos": 1000000,
  "currency": "USD",
  "pricing_lines": [],
  "key_id": "key-123",
  "throughput": null,
  "replay_supported": true,
  "replay_request": {
    "model": "openai/gpt-6-astra",
    "messages": [
      { "role": "user", "content": "Say hello" }
    ]
  }
}

Generation lookup lists every field.

Introduction

Text

Image

Audio

Specialised

Admin

Replay a stored request

Read the timing fields

Response

​Replay a stored request

​Read the timing fields

​Response

Replay a stored request

Read the timing fields

Response