OpenAI

Count input tokens

Count the tokens a request's input will consume

POST /openai/v1/responses/input_tokens○ Unsupported

Returns

501 This endpoint is not implemented yet; calling it returns the response below:

Counts the tokens the request input would consume without generating content. It depends on OpenAI Responses' official server-side storage (store) semantics, which we have not implemented yet; calling it returns 501 (message “This platform has not implemented … yet.”, with the x-should-retry header set to false), has no side effects, and the official SDK will not retry.

Errors follow the OpenAI format — see error codes

Response

HTTP 200

Native Responses API input token count

application/json

Name	Type	Description
$	object

POST

Count input tokens

The key is used only in your browser

Loading…

Response 501

{  "error": {    "message": "This platform has not implemented POST /v1/responses/input_tokens yet.",    "type": "api_error",    "param": null,    "code": "internal"  }}

Compact a responseUnsupported

Compact a model response's input into a summary.

Create a conversation

Create a new conversation