Get API key
InferenceCount tokens
Inference

Count tokens

An estimate of a Messages request's input tokens, from llm.buzz's own tokenizer, never the provider's. It costs nothing and is not refused for a key's spending limit. The body names the estimate in x-sgr-ignored-parameters as input_tokens->estimated(gateway_tokenizer).

View as MarkdownThe page as plain textOpen in ClaudeAsk questions about this pageOpen in ChatGPTAsk questions about this page
POST/api/v1/messages/count_tokens
Request
curl -X POST https://api.llm.buzz/api/v1/messages/count_tokens \
  -H "Authorization: Bearer $LLM_BUZZ_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-haiku-5.5",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in one word."
    }
  ]
}'
Response
{
  "input_tokens": 14,
  "x-sgr-ignored-parameters": [
    "input_tokens->estimated(gateway_tokenizer)"
  ]
}

Authorization

An inference key, as Authorization: Bearer KEY or in x-api-key, the header the Anthropic SDK sends.

Keys and limits

Body application/json

  • modelstringrequired

    A model's name from GET /api/v1/models, such as deepseek/deepseek-v4.1-flash. A suffix changes one request: :floor tries the cheapest provider first and :nitro the fastest. On Chat Completions and Responses :online asks for a web search, which llm.buzz does not run today: the request is served without one and x-sgr-ignored-parameters names web_search->dropped(search_unavailable), or for an organization whose requests llm.buzz keeps in the EU it answers 400 web_search_unavailable_in_region. On Messages :online does nothing and is named as model:online.

  • messagesobject[]required

    The conversation, as on Messages.

  • systemstring or object[]

    The system prompt: a string, or a list of text blocks, which may carry cache_control.

  • toolsobject[]

    Tools, as on Messages.

Response 200

The estimate.

Errors

  • 401

    Messages keeps Anthropic's error body: a 401 is an authentication_error, a 402 a billing_error, a 403 a permission_error and a 429 a rate_limit_error.

Every error code

Docs