Skip to main content
POST
/
v1
/
eval
Trigger an evaluation run
curl --request POST \
  --url https://api.trulayer.ai/v1/eval \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "trace_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "evaluator_type": "llm",
  "metric_name": "<string>",
  "config": {
    "provider": "anthropic",
    "model": "<string>",
    "model_tier": "cheap",
    "preset": "<string>",
    "prompt": "<string>"
  }
}
'
{
  "eval_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "pending"
}

Documentation Index

Fetch the complete documentation index at: https://docs.trulayer.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

SDK API key (tl_...) or Clerk session JWT

Body

application/json
​
trace_id
string<uuid>
required
​
evaluator_type
enum<string>
required
Available options:
llm,
rule
​
metric_name
string
required
​
config
object

Evaluator-specific configuration. Free-form for forward compatibility; recognised keys are documented below. Unknown keys are ignored.

Response

Eval queued

​
eval_id
string<uuid>
required
​
status
enum<string>
required
Available options:
pending,
running,
complete,
failed