Native Claude Format

Anthropic Claude Messages API requests. Requires the anthropic-version header.

Field	Value
Base URL	`https://token.easyapi.com/v1`
Authentication	Authorization: Bearer `API_KEY`
Example model	`claude-3-opus-20240229`
Format	Anthropic Messages compatible
Billing	Pay as you go

Note: Requests must include anthropic-version (e.g. 2023-06-01). Auth via Authorization: Bearer or x-api-key.

Example model

Examples below use claude-3-opus-20240229 (Claude 3 Opus). Replace model and adjust size, quality, etc. per console docs when switching models.

Create message

POSThttps://token.easyapi.com/v1/messages

Create a chat response using the Anthropic Claude Messages API format. Full path: POST /v1/messages.

Request parameters

Name	In	Type	Required	Description
`Authorization`	header	string	Yes	EasyAPI API Key. Format: Bearer `API_KEY`
`Content-Type`	header	string	Yes	Request body format, always application/json
`anthropic-version`	header	string	Yes	Anthropic API version, required, e.g. 2023-06-01
`x-api-key`	header	string	No	Anthropic API Key (optional; Bearer Token also works)

Request body

Name	Type	Required	Description
`model`	string	Yes	Model ID, e.g. claude-3-opus-20240229
`messages`	array<object>	Yes	Conversation messages, each with role and content
`max_tokens`	integer	Yes	Max output tokens, must be ≥ 1
`system`	string \| array<object>	No	System prompt as string or content block array
`temperature`	number	No	Sampling temperature, range 0–1
`top_p`	number	No	Nucleus sampling parameter
`top_k`	integer	No	Sample only from the top K tokens
`stream`	boolean	No	Enable streaming responses
`stop_sequences`	array<string>	No	Custom stop sequences
`tools`	array<object>	No	Tool definitions the model may call
`tool_choice`	object	No	Tool selection strategy
`thinking`	object	No	Extended thinking config (for supported models)
`metadata`	object	No	Request metadata

Example

{
  "model": "claude-3-opus-20240229",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 1024
}

Response example

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-3-opus-20240229",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 20,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0
  }
}