Skip to main content

Documentation Index

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

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

Use request inspection to debug failed or slow requests.

​
Save the Request ID

Inference responses include an x-request-id header. 
x-request-id: <REQUEST_ID>

​
List Requests

curl -s "https://api.wafer.ai/v1/endpoints/requests?endpoint=<ENDPOINT_HOST>&limit=20&errors_only=true" \
  -H "Authorization: Bearer <API_KEY>"

{
  "requests": [
    {
      "request_id": "<REQUEST_ID>",
      "status_code": 400,
      "model_requested": "<MODEL_ID>",
      "model_resolved": "<MODEL_ID>",
      "is_streaming": true,
      "ttft_ms": null,
      "total_latency_ms": 31,
      "input_tokens": 0,
      "output_tokens": 0,
      "cache_read_tokens": 0,
      "error_code": "invalid_json_request",
      "error_message": "Could not parse JSON body",
      "created_at": "<TIMESTAMP>"
    }
  ],
  "has_more": false,
  "cursor": null
}

​
Get One Request

curl -s "https://api.wafer.ai/v1/endpoints/requests/<REQUEST_ID>?endpoint=<ENDPOINT_HOST>" \
  -H "Authorization: Bearer <API_KEY>"
Example response: 
{
  "request_id": "<REQUEST_ID>",
  "status_code": 200,
  "model_requested": "<MODEL_ID>",
  "model_resolved": "<MODEL_ID>",
  "is_streaming": true,
  "ttft_ms": 428,
  "total_latency_ms": 2413,
  "input_tokens": 1180,
  "output_tokens": 241,
  "cache_read_tokens": 960,
  "error_code": null,
  "error_message": null,
  "created_at": "<TIMESTAMP>"
}

​
Parameters

  • endpoint (required): <ENDPOINT_HOST>
  • limit (optional, default 50): 1-200
  • cursor (optional): <CURSOR>
  • errors_only (optional): true or false

​
Key Fields

  • request_id: stable request ID
  • status_code: final HTTP status code
  • model_requested, model_resolved: requested and resolved model IDs
  • ttft_ms: time to first token
  • total_latency_ms: end-to-end latency
  • input_tokens, output_tokens, cache_read_tokens: token counts
  • error_code: Wafer error code when available
  • error_message: human-readable error description when available
  • created_at: UTC timestamp

​
Pagination

If has_more is true, pass the returned cursor value into the next request: 
curl -s "https://api.wafer.ai/v1/endpoints/requests?endpoint=<ENDPOINT_HOST>&limit=50&cursor=<CURSOR>" \
  -H "Authorization: Bearer <API_KEY>"

​
Error-Only Mode

Use errors_only=true to list only 4xx and 5xx requests.

​
Errors

  • 401: missing or invalid API key
  • 403: API key does not have access to the requested endpoint
  • 404: request ID was not found for that endpoint
  • 422: invalid cursor format or invalid request_id format (must be a UUID or 12-char hex x-request-id)

​
Notes

  • Request lookup is endpoint-scoped. A valid request ID for another endpoint returns 404.
  • Use x-request-id for exact correlation.