Count Tokens

Portkey supports the token counting endpoint from anthropic across vertex-ai, bedrock and anthropic in the same format. This allows use to use claude code and any other tooling with the same API signature across providers.

Examples

Python

import anthropic

client = anthropic.Anthropic(
    api_key="dummy", # we will use portkey's provider slug
    default_headers={"x-portkey-api-key": "YOUR_PORTKEY_API_KEY"},
    base_url="https://api.portkey.ai/v1"
)

response = client.messages.count_tokens(
    model="@your-provider-slug/your-model-name",
    system="You are a scientist",
    messages=[{
        "role": "user",
        "content": "Hello, Claude"
    }],
)

print(response.json())

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: 'dummy', // we will use portkey's provider slug
  baseURL: "https://api.portkey.ai/v1",
  defaultHeaders: { "x-portkey-api-key": "YOUR_PORTKEY_API_KEY" }
});

const response = await client.messages.countTokens({
  model: '@your-provider-slug/your-model-name',
  system: 'You are a scientist',
  messages: [{
    role: 'user',
    content: 'Hello, Claude'
  }]
});

console.log(response);

curl https://api.portkey.ai/v1/messages/count_tokens \
    --header "x-portkey-api-key: $PORTKEY_API_KEY" \
    --header "content-type: application/json" \
    --data '{
      "model": "@your-provider-slug/your-model-name",
      "system": "You are a scientist",
      "messages": [{
        "role": "user",
        "content": "Hello, Claude"
      }]
    }'