Available Models | Documentation | Geodd
Available Models
DocsServerless InferenceAvailable Models

Available Models

Retrieve a comprehensive, dynamic list of all AI models accessible via your specific API key.

Global (US)
https://api.geodd.io/inference/{key-slug}
Europe (EU)
https://eu.api.geodd.io/inference/{key-slug}

Authorizations

Authorization string header required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

key-slug string required

A unique identifier tied to your API key. This slug is automatically generated when you create a new key on the console UI, but it can be customized to any user-friendly string at any time.

Responses

200
OK
Request processed successfully. Returns a list of detailed model feature objects.
401
Unauthorized
Invalid or missing API Key. Check the Authorization header.
429
Too Many Requests
Token limit exceeded. Upgrade to a dedicated instance for higher limits.

Example Response:

The response returns detailed capabilities, pricing, and operational specifications for each allowed model on your key.

[
  {
    "id": "deepseek-ai/DeepSeek-V4-Flash",
    "name": "DeepSeek V4 Flash",
    "created": 1779196213,
    "input_modalities": [
      "text"
    ],
    "output_modalities": [
      "text"
    ],
    "quantization": "fp8",
    "context_length": 1048576,
    "max_output_length": 393216,
    "pricing": {
      "prompt": "0.000000140",
      "completion": "0.000000300",
      "image": "0",
      "request": "0",
      "input_cache_read": "0",
      "input_cache_write": "0"
    },
    "supported_sampling_parameters": [
      "temperature",
      "top_p",
      "top_k",
      "min_p",
      "frequency_penalty",
      "presence_penalty",
      "max_tokens",
      "seed",
      "stop"
    ],
    "supported_features": [
      "tools",
      "json_mode",
      "structured_outputs",
      "reasoning"
    ],
    "description": "This including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.",
    "openrouter": {
      "slug": "deepseek-ai/DeepSeek-V4-Flash"
    },
    "datacenter": "US",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash",
    "sortOrder": 0
  }
]