List Models

GET /v1/models

Returns all available models in OpenAI format. No authentication required.

Request

curl https://hyper.charm.land/v1/models

Response

{
  "object": "list",
  "data": [
    {
      "id": "deepseek-v4-pro",
      "object": "model",
      "created": 1784045313,
      "owned_by": "hyper",
      "display_name": "DeepSeek-V4-Pro",
      "context_window": 1000000,
      "max_output_tokens": 384000,
      "capabilities": {
        "vision": false
      },
      "reasoning": {
        "effort_levels": [
          {
            "value": "high",
            "display": "High"
          },
          {
            "value": "xhigh",
            "display": "X-High"
          }
        ],
        "default_effort_level": "high"
      },
      "pricing": {
        "input": 2.4,
        "output": 4.8,
        "cache_create": 0,
        "cache_hit": 0.2
      }
    }
  ]
}

Field	Description
id	Model ID to use in API requests
display_name	Human-readable name
context_window	Max input tokens
max_output_tokens	Max output tokens
capabilities.vision	Whether the model supports vision (image attachments)
reasoning.effort_levels	List of available effort levels (e.g. ["low", "medium", "high"])
reasoning.default_effort_level	Default effort level (e.g. medium")
pricing	Per-million-token pricing

Errors

This endpoint does not require authentication and rarely returns errors. When it does, they use the standard OpenAI error format:

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