Count tokens

POST /messages/count_tokens

Count the input tokens a Messages request would consume, without running it. Same request shape as POST /messages (minus max_tokens); free.

POST
/messages/count_tokens

Authorization

AuthorizationBearer <token>

Your Munito API key.

In: header

Header Parameters

munito-service-tier?string

priority, standard or flex. The response names the tier that is billed; see x-ratelimit-over-limit.

Default"standard"

Value in

  • "priority"
  • "standard"
  • "flex"
munito-affinity?string

An opaque token. Send it back with the next request of the conversation, so that the prompt cache can serve it.

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model*string

Model id from GET /models.

messages*array<>

The messages to count, Anthropic-style.

Response Body

application/json

curl -X POST "https://example.com/messages/count_tokens" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-27b",
    "messages": [
      {
        "role": "user",
        "content": "Explain intelligence sovereignty in one sentence."
      }
    ]
  }'
{
  "input_tokens": 18
}