Get model schema
package main
import ( "fmt" "net/http" "io")
func main() {
url := "https://api.ai.wpengine.com/v1/models/anthropic/claude-haiku-4-5/schema"
req, _ := http.NewRequest("GET", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close() body, _ := io.ReadAll(res.Body)
fmt.Println(res) fmt.Println(string(body))
}const url = 'https://api.ai.wpengine.com/v1/models/anthropic/claude-haiku-4-5/schema';const options = {method: 'GET'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}<?php
$client = new \GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.ai.wpengine.com/v1/models/anthropic/claude-haiku-4-5/schema');
echo $response->getBody();curl --request GET \ --url https://api.ai.wpengine.com/v1/models/anthropic/claude-haiku-4-5/schemaReturns the generated request (input) and response (output) JSON Schemas for a single model. The model ID is namespaced as “owner/name”, where owner is the model’s vendor (anthropic, google, …). The schemas describe the chat completion contract, so only chat-capable models are served; unknown or non-chat models return 404. No authentication is required.
Parameters
Section titled “Parameters”Path Parameters
Section titled “Path Parameters”Owner (vendor) segment of the namespaced model ID.
Example
anthropicModel-name segment of the namespaced model ID.
Example
claude-haiku-4-5Responses
Section titled “Responses”Generated input and output JSON Schemas for the model
Per-model JSON Schemas. input_schema validates a chat completion request body for this model (with model-specific parameter constraints baked in); output_schema describes the chat completion response. Both are JSON Schema 2020-12 documents emitted as free-form objects.
object
The namespaced model ID the schemas were generated for.
JSON Schema (2020-12) for the chat completion request body.
object
JSON Schema (2020-12) for the chat completion response body.
object
Example
{ "id": "anthropic/claude-haiku-4-5"}Invalid request body or parameters
object
object
Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.
Example
{ "error": { "type": "invalid_request_error", "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5" }}The requested resource was not found
object
object
Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.
Example
{ "error": { "type": "invalid_request_error", "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5" }}Rate limit exceeded. The request was throttled at the edge; wait and retry later. The response body is a short HTML page generated by the load balancer, not a structured JSON error — clients should rely on the 429 status code rather than parsing the body.