Available Models

Retrieve a comprehensive, dynamic list of AI models — scoped to your API key when authenticated, or the full public catalog when called without a key.

Global (US)

https://api.geodd.io/inference/v1/models

Europe (EU)

https://eu.api.geodd.io/inference/v1/models

Authorization (Optional)

Authorization string header optional

This endpoint works with or without an API key:

With Bearer <token>: the catalog is scoped to the models allowed on your key's service, with capacity resolved for your user (defaults plus your user-level overrides).
Without Authorization: returns the full public catalog — every available model with its pricing, capacity, and options — scoped to the public service.

When provided, the format is Bearer <token>. An invalid key returns 401.

Get a Single Model

modelId string path required

Retrieve one model by id via GET /inference/v1/models/:modelId (e.g. zai-org/glm-5.2), URL-encoded if it contains slashes. Returns 404 if the model is not found or not allowed for your API key.

Responses

200

Request processed successfully. Returns a list of detailed model feature objects.

401

Unauthorized

The provided API key is invalid. Check the Authorization header, or omit it for the public catalog.

429

Too Many Requests

Token limit exceeded. Upgrade to a dedicated instance for higher limits.

Example Response:

The response follows the OpenRouter Provider Monitor Schema 2.4, returning detailed capabilities, pricing, capacity limits, and operational specifications for each allowed model on your key.

Response Fields

Each model entry includes:

schema_version — schema version string (currently 2.4)
id, name, hugging_face_id — model identifiers
quantization and description — only when present
input_modalities / output_modalities — with context/output limits, per-token USD pricing, and capacity descriptors
capacity — at the model root, the request RPM limit
openrouter, datacenters, compliance — only when present
is_ready — defaults to true

Capacity descriptors are resolved from defaults with your user-level overrides applied on top:

model root: request RPM
text input modality: prompt TPM
text output modality: completion TPM and concurrency (no per)

Missing limits are omitted; no empty capacity arrays are emitted.

1{
2  "data": [
3    {
4      "schema_version": "2.4",
5      "id": "zai-org/glm-5.2",
6      "name": "GLM 5.2",
7      "hugging_face_id": "zai-org/glm-5.2",
8      "quantization": "fp8",
9      "input_modalities": [
10        {
11          "type": "text",
12          "supported_inputs": {
13            "max_context_length": {
14              "value": 1048576,
15              "unit": "token"
16            }
17          },
18          "pricing": [
19            {
20              "type": "prompt",
21              "unit": "token",
22              "cost_usd": "0.00000090"
23            }
24          ],
25          "capacity": [
26            {
27              "type": "prompt",
28              "unit": "token",
29              "per": "minute",
30              "value": 50000000
31            }
32          ]
33        }
34      ],
35      "output_modalities": [
36        {
37          "type": "text",
38          "max_length": {
39            "value": 131072,
40            "unit": "token"
41          },
42          "streaming": true,
43          "pricing": [
44            {
45              "type": "completion",
46              "unit": "token",
47              "cost_usd": "0.00000280"
48            }
49          ],
50          "capacity": [
51            {
52              "type": "completion",
53              "unit": "token",
54              "per": "minute",
55              "value": 500000
56            },
57            {
58              "type": "concurrency",
59              "unit": "request",
60              "value": 100
61            }
62          ]
63        }
64      ],
65      "openrouter": {
66        "slug": "z-ai/glm-5.2"
67      },
68      "datacenters": [
69        {
70          "country_code": "US",
71          "region": "us-east"
72        }
73      ],
74      "compliance": {
75        "zdr": true
76      },
77      "is_ready": true,
78      "capacity": [
79        {
80          "type": "request",
81          "unit": "request",
82          "per": "minute",
83          "value": 100
84        }
85      ]
86    }
87  ]
88}

Quick Start

Chat Completion