Anthropic Messages

POST /v1/messages

Anthropic Messages API compatible endpoint.

See Anthropic's documentation for the full request and response specification.

INFO

For compatibility with Claude Code and other compatible agents, the /v1/messages endpoint also supports the X-Api-Key header for authentication.

Request

curl https://hyper.charm.land/v1/messages \
  -H "x-api-key: sk-hyper-xxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Field	Type	Required	Description
model	string	yes	Model ID from /v1/models
max_tokens	integer	yes	Max output tokens
messages	array	yes	Array of message objects
system	string or array	no	System prompt
stream	boolean	no	Set true for SSE streaming

All standard Anthropic parameters are accepted.

Response

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {"type": "text", "text": "Hey there!"}
  ],
  "model": "deepseek-v4-pro",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 5
  }
}

Errors

All errors use the Anthropic error format:

{
  "type": "error",
  "error": {
    "type": "...",
    "message": "..."
  }
}

Status	error.type	Cause
400	invalid_request_error	Invalid JSON, missing model, messages, or max_tokens, context window exceeded
401	authentication_error	Missing or invalid x-api-key
403	permission_error	Forbidden
404	not_found_error	Model not found
429	rate_limit_error	Rate limit exceeded
5xx	api_error	Upstream provider failure