Count Anthropic Messages input tokens

POST

messages

count_tokens

curl --request POST \
  --url https://api.abliteration.ai/v1/messages/count_tokens \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "system": "<string>",
  "tools": [
    {}
  ],
  "tool_choice": {
    "name": "<string>",
    "disable_parallel_tool_use": true
  },
  "thinking": {
    "budget_tokens": 499995
  },
  "output_config": {
    "format": {
      "type": "json_schema",
      "schema": {}
    }
  },
  "context_management": {
    "edits": [
      {
        "type": "clear_thinking_20251015",
        "keep": "all"
      }
    ]
  }
}
'

import requests

url = "https://api.abliteration.ai/v1/messages/count_tokens"

payload = {
    "model": "<string>",
    "messages": [{ "content": "<string>" }],
    "system": "<string>",
    "tools": [{}],
    "tool_choice": {
        "name": "<string>",
        "disable_parallel_tool_use": True
    },
    "thinking": { "budget_tokens": 499995 },
    "output_config": { "format": {
            "type": "json_schema",
            "schema": {}
        } },
    "context_management": { "edits": [
            {
                "type": "clear_thinking_20251015",
                "keep": "all"
            }
        ] }
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [{content: '<string>'}],
    system: '<string>',
    tools: [{}],
    tool_choice: {name: '<string>', disable_parallel_tool_use: true},
    thinking: {budget_tokens: 499995},
    output_config: {format: {type: 'json_schema', schema: {}}},
    context_management: {edits: [{type: 'clear_thinking_20251015', keep: 'all'}]}
  })
};

fetch('https://api.abliteration.ai/v1/messages/count_tokens', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "input_tokens": 1
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

Headers

Authorization

string | null

Bearer API key.

x-api-key

string | null

API key alternative for Anthropic-compatible clients. Authorization takes precedence when both headers are present.

Body

application/json

Anthropic Messages count-tokens-compatible request.

model

string

required

Minimum string length: 1

messages

AnthropicMessage · object[]

required

Minimum array length: 1

Show child attributes

system

tools

Tools · object[] | null

tool_choice

AnthropicToolChoice · object | null

Show child attributes

thinking

AnthropicThinking · object | null

Show child attributes

output_config

AnthropicOutputConfig · object | null

Show child attributes

context_management

AnthropicContextManagement · object | null

Supported beta context-management subset.

keep=all does not remove any replayed thinking blocks, so it can be safely consumed at the compatibility boundary and omitted from the vLLM provider payload.

Show child attributes

Response

Successful Response

input_tokens

integer

required

Required range: x >= 0

Count Anthropic Messages input tokens

curl --request POST \
  --url https://api.abliteration.ai/v1/messages/count_tokens \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "system": "<string>",
  "tools": [
    {}
  ],
  "tool_choice": {
    "name": "<string>",
    "disable_parallel_tool_use": true
  },
  "thinking": {
    "budget_tokens": 499995
  },
  "output_config": {
    "format": {
      "type": "json_schema",
      "schema": {}
    }
  },
  "context_management": {
    "edits": [
      {
        "type": "clear_thinking_20251015",
        "keep": "all"
      }
    ]
  }
}
'

import requests

url = "https://api.abliteration.ai/v1/messages/count_tokens"

payload = {
    "model": "<string>",
    "messages": [{ "content": "<string>" }],
    "system": "<string>",
    "tools": [{}],
    "tool_choice": {
        "name": "<string>",
        "disable_parallel_tool_use": True
    },
    "thinking": { "budget_tokens": 499995 },
    "output_config": { "format": {
            "type": "json_schema",
            "schema": {}
        } },
    "context_management": { "edits": [
            {
                "type": "clear_thinking_20251015",
                "keep": "all"
            }
        ] }
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [{content: '<string>'}],
    system: '<string>',
    tools: [{}],
    tool_choice: {name: '<string>', disable_parallel_tool_use: true},
    thinking: {budget_tokens: 499995},
    output_config: {format: {type: 'json_schema', schema: {}}},
    context_management: {edits: [{type: 'clear_thinking_20251015', keep: 'all'}]}
  })
};

fetch('https://api.abliteration.ai/v1/messages/count_tokens', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "input_tokens": 1
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "auth_error",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

API Reference

Inference API

Policy API

Administration API

Count Anthropic Messages input tokens

Headers

Body

Response