Documentacao API

Claude Fable 5 API

Claude Fable 5 oferece long-context reasoning, coding, vision e agentic workflows via uma Messages API compativel com Claude com janela de contexto de 1M tokens.

Endpoint

POST https://api.defapi.org/api/v1/messages

Model

anthropic/claude-fable-5

Preco

$5 input / $25 output per 1M tokens

Autenticacao

Envie sua API key no header Authorization usando o formato Bearer token.

Authorization: Bearer <your-api-key>

Criar um Message

O endpoint e compativel com Claude-style Messages requests e suporta respostas JSON non-streaming e streaming responses.

curl https://api.defapi.org/api/v1/messages \
  -H "Authorization: Bearer dk-1234567890abcdef" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-fable-5",
    "messages": [
      {
        "role": "user",
        "content": "Explain how to migrate a large Next.js codebase."
      }
    ],
    "max_tokens": 512,
    "temperature": 0.7,
    "stream": false
  }'

Request Parameters

Nome	Tipo	Descricao
model	string	Required. Use anthropic/claude-fable-5.
messages	array	Required. Conversation messages with role and content.
max_tokens	integer	Maximum number of tokens to generate.
temperature	number	Controls randomness. Supported range: 0 to 2.
top_p	number	Nucleus sampling parameter. Supported range: 0 to 1.
stream	boolean	Set true to receive server-sent event style streaming.
stop	string	Up to 4 sequences where generation should stop.
user	string	A unique identifier for your end user.

Streaming request

Defina stream como true para receber chunks no estilo server-sent events.

{
  "model": "anthropic/claude-fable-5",
  "messages": [
    {
      "role": "user",
      "content": "Tell me a short story about a brave knight."
    }
  ],
  "max_tokens": 512,
  "temperature": 0.7,
  "stream": true
}

Non-streaming response

Um request non-streaming bem-sucedido retorna assistant message e token usage.

{
  "id": "msg_01ABCDxyz",
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-fable-5",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "usage": {
    "input_tokens": 20,
    "output_tokens": 50,
    "cache_read_input_tokens": 0,
    "cache_creation_input_tokens": 0
  }
}

Error responses

400

Bad request

Parametros invalidos ou campos obrigatorios ausentes.

401

Unauthorized

API key invalida ou ausente.

500

Internal server error

Falha server-side inesperada.