Count tokens in a Message | PrivateGPT

curl -X POST https://host.com/v1/messages/count_tokens \
     -H "Content-Type: application/json" \
     -d '{
  "model": "default",
  "messages": [
    {
      "role": "user",
      "content": "Count tokens for this input."
    }
  ],
  "system": [
    {
      "text": "You are a tokenizer."
    }
  ],
  "tools": [
    {
      "name": "get_weather",
      "description": "Get current weather for a city.",
      "inputSchema": {
        "properties": {
          "city": {
            "description": "City name.",
            "type": "string"
          }
        },
        "required": [
          "city"
        ],
        "type": "object"
      }
    }
  ],
  "thinking": {
    "enabled": false
  },
  "tool_choice": {
    "type": "auto",
    "disable_parallel_tool_use": false,
    "validation_mode": "lazy"
  }
}'

Count tokens in a Message

Request

This endpoint expects an object.

modelstringRequiredDefaults to default

Model identifier or alias.

messageslist of objectsRequired

Conversation messages for the request.

systemlist of objectsOptional

System prompt input. Accepts str, list[str], System, list[System], or null. It is normalized internally to list[System].

toolslist of objectsOptional

Optional tool definitions.

thinkingobjectOptional

Thinking configuration.

tool_choiceobjectOptional

Tool selection policy.

output_configobjectOptional

Optional output configuration options.

cache_controlobjectOptional

Optional request-level cache control.

Response

This endpoint returns an object.

input_tokensinteger

Estimated number of input tokens for the provided payload.

Errors

401

Unauthorized

422

Unprocessable Entity

1	{
2	"input_tokens": 1
3	}