Token Counting

Use POST /v1/messages/count_tokens to count how many input tokens a request would consume — without actually running the model. The request forwards to Anthropic with the token-counting beta header. Claude models only.

Endpoint

POST https://api.tokapi.ai/v1/messages/count_tokens

The body is a standard Messages request without max_tokens.

Example

curl https://api.tokapi.ai/v1/messages/count_tokens \
  -H "Authorization: Bearer sk-lazytech-..." \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{ "role": "user", "content": "How many tokens is this?" }]
  }'

Response

{ "input_tokens": 14 }

Use this to estimate context size before sending a full request. Available for Claude models only.