OpenAI Responses

POST /v1/responses

OpenAI Responses API compatible endpoint. This is a standard pass-through.

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

Request

curl https://hyper.charm.land/v1/responses \
  -H "Authorization: Bearer sk-hyper-xxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "input": "What is bubble tea?"
  }'

Field	Type	Required	Description
model	string	yes	Model ID from /v1/models
input	string or array	yes	A string prompt or array of message objects

All standard Responses API parameters are accepted.

Response

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1718000000,
  "model": "deepseek-v4-pro",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Bubble tea is a Taiwanese drink..."
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 42,
    "total_tokens": 50
  }
}

Errors

All errors use the standard OpenAI error format:

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

Status	error.type	Cause
400	invalid_request_error	Invalid JSON, missing model or input, context window exceeded
401	authentication_error	Missing or invalid API key
402	billing_error	Insufficient Hypercredits
403	permission_error	Forbidden
404	invalid_request_error	Model not found
429	rate_limit_error	Rate limit exceeded
5xx	server_error	Upstream provider failure