Count input tokens

Count the tokens in the fully rendered input for a Responses request, without generating or storing a response. The count includes resolved previous_response_id history, current instructions and tools, media, and server-injected prompt scaffolding. Conversation resources are not supported.

POST /responses/input_tokens

Count tokens in the fully rendered input for a Responses request without generating or storing a response.

Request body

Content Type: application/json

CreateResponse

Response

HTTP 200 — Success

Content Type: application/json

TokenCountsResource

python
import json
import os
​
import requests
​
response = requests.post(
    "https://api.meta.ai/v1/responses/input_tokens",
    headers={
        "Authorization": f"Bearer {os.environ['MODEL_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "muse-spark-1.3",
        "input": "What is the capital of France?",
    },
)
response.raise_for_status()
print(json.dumps(response.json(), indent=2))

shell
curl -X POST "https://api.meta.ai/v1/responses/input_tokens" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "muse-spark-1.3",
  "input": "What is the capital of France?"
}'

For usage examples and rate-limit guidance, see the Responses feature page.