Responses Input Tokens

Count the input tokens of a Responses API request without calling the model.

Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/input-tokens

curl -X POST http://localhost:4000/v1/responses/input_tokens     -H "Content-Type: application/json"     -H "Authorization: Bearer $LITELLM_MASTER_KEY"     -d '{
    "model": "gpt-4o",
    "input": "Hello, how are you?"
}'

Returns: {"object": "response.input_tokens", "input_tokens": <count>}