List models

GET/v1/models

List models available through Token360.

The response uses the OpenAI-compatible model list shape. Use the returned id as the model value in compatible endpoints such as chat completions, image generation, video generation, audio, and batch jobs.

Authentication

No authentication is required. API keys sent as Authorization: Bearer ... are accepted but not required.

Query Parameters

currentinteger

Page number.

sizeinteger

Page size.

sort_byenum<string>

Sort field.

sort_orderenum<string>

Sort direction.

model_typestring

Filter by model type, such as LLM, IMAGE_GENERATION, VIDEO_GENERATION, or AUDIO.

keywordstring

Search by model name or display name.

namestring

Exact model name filter. Multiple names may be comma-separated.

tagsstring

Filter by one or more comma-separated tags.

input_typesstring

Filter by comma-separated input types, such as text,image,audio.

output_typesstring

Filter by comma-separated output types, such as text,image,video,audio.

publisher_namesstring

Filter by one or more publisher display names. May be comma-separated or sent multiple times.

Response

objectstring

Always list.

dataobject[]

List of model objects.

data.idstring

Model ID to pass as the model parameter.

data.objectstring

Always model.

data.createdinteger

Unix timestamp derived from the model publish or update time.

data.owned_bystring

Publisher or owner display name.

data.architectureobject

Model architecture and modality metadata.

data.canonical_slugstring

Model slug. Matches id.

data.context_lengthinteger|null

Maximum prompt plus completion tokens when derivable from the model API Usage schema.

data.default_parametersobject

Default request parameter values applied or recommended for this model when available.

data.parameter_schemaobject

Supported request parameter metadata keyed by supported parameter name.

data.descriptionstring

Model description.

data.expiration_datestring|null

Expiration date when available; otherwise null.

data.hugging_face_idstring|null

Hugging Face model identifier when available; otherwise null.

data.knowledge_cutoffstring|null

Training-data cutoff date when available; otherwise null.

data.linksobject

Related model resources.

data.namestring

Display name.

data.per_request_limitsobject

Per-request limits derived from the normalized API Usage schema.

data.supported_parametersstring[]

Supported request parameter names from the same normalized API Usage schema shown on the model detail page.

data.supported_voicesstring[]|null

Supported voice IDs for voice models when available; otherwise null.

Request

Shell

1curl https://api.token360.ai/v1/models

Response

JSON

1{
2  "object": "list",
3  "data": [
4    {
5      "architecture": {
6        "input_modalities": ["text", "image", "video"],
7        "output_modalities": ["text"],
8        "tokenizer": null
9      },
10      "canonical_slug": "qwen3.5-flash",
11      "context_length": null,
12      "created": 1780324099,
13      "default_parameters": {
14        "frequency_penalty": 0,
15        "presence_penalty": 0,
16        "temperature": 0.7,
17        "top_p": 1
18      },
19      "description": "",
20      "expiration_date": null,
21      "hugging_face_id": null,
22      "id": "qwen3.5-flash",
23      "knowledge_cutoff": null,
24      "links": {
25        "details": "/models/qwen3.5-flash"
26      },
27      "name": "Qwen3.5 Flash",
28      "object": "model",
29      "owned_by": "Qwen",
30      "per_request_limits": {
31        "completion_tokens": 4096,
32        "prompt_tokens": null
33      },
34      "supported_parameters": [
35        "temperature",
36        "top_p",
37        "max_completion_tokens",
38        "presence_penalty",
39        "frequency_penalty"
40      ],
41      "parameter_schema": {
42        "temperature": {
43          "type": "number",
44          "options": null,
45          "default": 0.7,
46          "min": 0,
47          "max": 2
48        },
49        "top_p": {
50          "type": "number",
51          "options": null,
52          "default": 1,
53          "min": 0,
54          "max": 1
55        },
56        "max_completion_tokens": {
57          "type": "number",
58          "options": null,
59          "default": 4096,
60          "min": 1,
61          "max": 65536
62        },
63        "presence_penalty": {
64          "type": "number",
65          "options": null,
66          "default": 0,
67          "min": -2,
68          "max": 2
69        },
70        "frequency_penalty": {
71          "type": "number",
72          "options": null,
73          "default": 0,
74          "min": -2,
75          "max": 2
76        }
77      },
78      "supported_voices": null
79    }
80  ]
81}

Was this page helpful?