import weflayr
from uuid import UUID
client = weflayr.client() # reads WEFLAYR_API_KEY
client.get_benchmark_examples(benchmark_uuid=UUID("5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01"), limit=2)
const weflayr = require('weflayr');
const client = weflayr.client(); // reads WEFLAYR_API_KEY
await weflayr.api.getBenchmarkExamples({
client,
throwOnError: true,
query: {
benchmarkUuid: '5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01',
limit: 2,
},
});
curl "https://app.weflayr.com/api/benchmark-examples/?benchmark_uuid=5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01&limit=2" \
-H "Authorization: Bearer $WEFLAYR_API_KEY"
{
"examples": [
{
"id": "evt_8f2a",
"customer_name": "Meridian Health",
"timestamp": "2026-10-12T08:41:00+00:00",
"verdicts": {
"gpt-6-luna": {
"1": "same"
}
},
"model": null,
"is_baseline_model_pick": null,
"reasoning_effort": null
}
],
"example": null,
"next_cursor": null,
"has_more": false,
"blockers": []
}
{"error": "Invalid or missing API key. Send it as \"Authorization: Bearer <your key>\"."}
{"error": "No benchmark of this project has the id 5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01. List the project's benchmarks with get_benchmarks."}
{"error": "The benchmark is running, so it has no results to read yet. Read it again with get_benchmark once its status is completed.", "code": "benchmark_not_finished"}
{"error": "Invalid request payload.", "detail": [{"field": "benchmark_uuid", "error": "Field required"}]}
Benchmarks
Get benchmark examples
Get the examples of a finished benchmark.
GET
/
api
/
benchmark-examples
/
import weflayr
from uuid import UUID
client = weflayr.client() # reads WEFLAYR_API_KEY
client.get_benchmark_examples(benchmark_uuid=UUID("5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01"), limit=2)
const weflayr = require('weflayr');
const client = weflayr.client(); // reads WEFLAYR_API_KEY
await weflayr.api.getBenchmarkExamples({
client,
throwOnError: true,
query: {
benchmarkUuid: '5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01',
limit: 2,
},
});
curl "https://app.weflayr.com/api/benchmark-examples/?benchmark_uuid=5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01&limit=2" \
-H "Authorization: Bearer $WEFLAYR_API_KEY"
{
"examples": [
{
"id": "evt_8f2a",
"customer_name": "Meridian Health",
"timestamp": "2026-10-12T08:41:00+00:00",
"verdicts": {
"gpt-6-luna": {
"1": "same"
}
},
"model": null,
"is_baseline_model_pick": null,
"reasoning_effort": null
}
],
"example": null,
"next_cursor": null,
"has_more": false,
"blockers": []
}
{"error": "Invalid or missing API key. Send it as \"Authorization: Bearer <your key>\"."}
{"error": "No benchmark of this project has the id 5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01. List the project's benchmarks with get_benchmarks."}
{"error": "The benchmark is running, so it has no results to read yet. Read it again with get_benchmark once its status is completed.", "code": "benchmark_not_finished"}
{"error": "Invalid request payload.", "detail": [{"field": "benchmark_uuid", "error": "Field required"}]}
Get the examples of a completed or archived benchmark: the calls it replayed, or the validation examples of one optimization objective with the model its router picked. Give an example_id to read one in full, with each model’s answer, usage and verdicts.
The response also carries
Parameters
string
required
The benchmark’s id.
string
Read the validation examples of this optimization objective, with the model its router picked. Omit to read the replayed calls. One of
same_quality_lowest_cost, same_cost_best_quality or best_quality.string
Read this example in full: the call, each model’s answer, its usage and its verdicts. Omit to list the examples.
string
default:"\"\""
Keep the examples whose prompt, customer or id has this text.
string
The route is paginated: pass the previous page’s
next_cursor, as is, to get the next page. has_more says whether another page exists.integer
default:"100"
Number of examples per page. Max
1000.blockers (what prevents the usual next step), in plain words. It is empty when the usual workflow applies.
import weflayr
from uuid import UUID
client = weflayr.client() # reads WEFLAYR_API_KEY
client.get_benchmark_examples(benchmark_uuid=UUID("5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01"), limit=2)
const weflayr = require('weflayr');
const client = weflayr.client(); // reads WEFLAYR_API_KEY
await weflayr.api.getBenchmarkExamples({
client,
throwOnError: true,
query: {
benchmarkUuid: '5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01',
limit: 2,
},
});
curl "https://app.weflayr.com/api/benchmark-examples/?benchmark_uuid=5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01&limit=2" \
-H "Authorization: Bearer $WEFLAYR_API_KEY"
{
"examples": [
{
"id": "evt_8f2a",
"customer_name": "Meridian Health",
"timestamp": "2026-10-12T08:41:00+00:00",
"verdicts": {
"gpt-6-luna": {
"1": "same"
}
},
"model": null,
"is_baseline_model_pick": null,
"reasoning_effort": null
}
],
"example": null,
"next_cursor": null,
"has_more": false,
"blockers": []
}
{"error": "Invalid or missing API key. Send it as \"Authorization: Bearer <your key>\"."}
{"error": "No benchmark of this project has the id 5c1d6a52-3f5f-4c53-9a0e-6f2b9c7d8e01. List the project's benchmarks with get_benchmarks."}
{"error": "The benchmark is running, so it has no results to read yet. Read it again with get_benchmark once its status is completed.", "code": "benchmark_not_finished"}
{"error": "Invalid request payload.", "detail": [{"field": "benchmark_uuid", "error": "Field required"}]}