Skip to content
WP EngineDocumentation

Count message tokens (Anthropic Messages API)

POST
/v1/messages/count_tokens
<?php


$client = new \GuzzleHttp\Client();


$response = $client->request('POST', 'https://api.ai.wpengine.com/v1/messages/count_tokens', [
  'body' => '{ "model": "anthropic/claude-sonnet-4-6", "messages": [ { "role": "user", "content": "example" } ], "system": "example" }',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);


echo $response->getBody();

Counts the input tokens a Messages request would consume, without creating a message or incurring model usage. Accepts the same request shape as /v1/messages minus max_tokens. Authentication matches /v1/messages: a WP Engine bearer token or an “x-api-key” header; API keys must carry the “chat:write” permission. Some models do not support token counting and return a 400 error.

Authorizations

Section titled “Authorizations”

Request Bodyrequired

Section titled “Request Bodyrequired”
Media typeapplication/json

Same shape as an Anthropic Messages request without max_tokens; system and tools are included in the count when supplied.

object
model
required
string
Example
anthropic/claude-sonnet-4-6
messages
required
Array<object>
object
role
required
string
Allowed values: user assistant
content
required

Message content: a plain string, or an array of content blocks (text, image, tool_use, tool_result, thinking, …).

system

System prompt, as a string or array of content blocks.

Responses

Section titled “Responses”

200

Section titled “200”

Token count for the supplied request

Media typeapplication/json
object
input_tokens
required

Tokens the supplied request would consume as input.

integer
Example
{
  "input_tokens": 14
}

400

Section titled “400”

Invalid request body or parameters, in Anthropic error envelope format (error type “invalid_request_error”).

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

401

Section titled “401”

Missing or invalid credentials, in Anthropic error envelope format (error type “authentication_error”).

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

Headers

Section titled “Headers”
WWW-Authenticate
string
Example
Bearer realm="ai-services"

403

Section titled “403”

Valid credentials but insufficient permission, in Anthropic error envelope format (error type “permission_error”). On /v1/messages specifically, a 403 with error type “content_policy_violation” instead means the request content was blocked by content moderation policy; that response never identifies which filter or category matched.

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

404

Section titled “404”

The requested model was not found or does not support this endpoint, in Anthropic error envelope format (error type “not_found_error”).

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

413

Section titled “413”

Request body exceeds the size limit, in Anthropic error envelope format (error type “request_too_large”).

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

429

Section titled “429”

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.

Media typetext/html
string

502

Section titled “502”

Upstream provider returned an error, in Anthropic error envelope format (error type “api_error”).

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

503

Section titled “503”

A required dependency (such as the authorization service) is temporarily unavailable, in Anthropic error envelope format (error type “overloaded_error”). Retry after a short delay with exponential back-off.

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

default

Section titled “default”

Upstream provider error relayed with its original status code and translated into Anthropic error envelope format. The error type reflects the status code (e.g. “rate_limit_error” for 429, “overloaded_error” for 529).

Media typeapplication/json

Anthropic error envelope, as parsed by Anthropic SDKs.

object
type
required
string
Allowed values: error
error
required
object
type
required

Anthropic error type, e.g. “invalid_request_error”, “authentication_error”, “permission_error”, “not_found_error”, “request_too_large”, “rate_limit_error”, “overloaded_error”, “api_error”, or “content_policy_violation” (request content blocked by moderation policy — never identifies which filter or category matched).

string
message
required
string
request_id

Correlation ID for this request, matching the X-Request-ID response header. Quote it in support reports.

string
Example
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required and must be greater than zero",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}