/messages/count_tokens

Count tokens in messages without generating a response. Useful for estimating costs and staying within context limits.

POST
/v1/messages/count_tokens

Count the number of tokens in a message without generating a response. This endpoint does not incur generation costs.

Request Body

modelThe model to use for tokenization (required)
messagesMessages to count tokens for (required)
Request Body
{
  "model": "your-model",
  "messages": [
    {"role": "user", "content": "Hello, how are you?"}
  ]
}