---
title: "/v1/models"
description: "List the models available to your workspace."
section: api-reference
order: 3
layout: api-reference
updated: "2026-07-30"
---

`GET /v1/models`

List every model your API key can call. OpenAI-compatible wire shape — the `openai` SDKs work with a `base_url` swap to `https://api.tokenfactory.omniva.com/v1`.

Use this endpoint for programmatic model discovery. The richer dashboard catalog (capabilities, pricing, benchmarks) is intentionally not on this surface — see the contrast in [Models overview](/docs/getting-started/models-overview).

## Authentication

Bearer token in the `Authorization` header. See [Authentication](/docs/getting-started/authentication) for how to mint and rotate keys.

```http
Authorization: Bearer $OMNIVA_API_KEY
```

## Request

No request body. No query parameters. The list returned is scoped to the workspace that owns the API key.

## Response

Returns a `list` object whose `data` contains one `model` entry per callable model.

`HTTP 200` `application/json`

```json
{
  "object": "list",
  "data": [
    {
      "id": "Omniva/glm-5.3",
      "object": "model",
      "created": 0,
      "owned_by": "Omniva"
    }
  ]
}
```

### Response fields

- `object` — always `"list"`.
- `data[].id` — provider-prefixed model identifier. Pass this as `model` to `/v1/chat/completions`, `/v1/embeddings`, and other endpoints.
- `data[].object` — always `"model"`.
- `data[].created` — Unix timestamp, may be `0` if the model has no provider-published creation date.
- `data[].owned_by` — provider or org that owns the model.

This list reflects the shared model catalog. If your workspace has [dedicated endpoints](/docs/dedicated-endpoints/what-are-dedicated-endpoints), don't rely on this endpoint to discover their Model IDs — it does not return them.

There are two places to get them:

- **Programmatically:** `GET /v1/endpoints`. Each entry's `status.inferenceModelId` is the exact string to pass as `model`. Use this one from code — it needs no console session. Guard for its absence: `status` is not populated while an endpoint is still provisioning.
- **By hand:** each endpoint's entry in the console.

See [Call a dedicated endpoint](/docs/dedicated-endpoints/call-endpoint#where-to-find-the-model-id) for the full flow, and [the endpoints API](/docs/api-reference/endpoints) for the response shape.

## Errors

| Status | Code | When |
|---|---|---|
| 401 | `unauthorized` | Missing `Authorization` header or non-Bearer scheme. |
| 401 | `invalid_api_key` | Bearer token did not resolve to a live API key. |
| 500 | `internal_error` | Unexpected gateway failure — retry with backoff. |
| 503 | `upstream_unavailable` | Catalog backend is unreachable — retry with backoff. |

See [Errors](/docs/reference/errors) for the full error envelope and retry guidance.

## Code samples

  
**Python**

```python
from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["OMNIVA_API_KEY"],
    base_url="https://api.tokenfactory.omniva.com/v1",
)

models = client.models.list()
for m in models.data:
    print(m.id)
```

  
**TypeScript**

```typescript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OMNIVA_API_KEY,
  baseURL: "https://api.tokenfactory.omniva.com/v1",
});

const models = await client.models.list();
for (const m of models.data) {
  console.log(m.id);
}
```

  
**cURL**

```bash
curl https://api.tokenfactory.omniva.com/v1/models \
  -H "Authorization: Bearer $OMNIVA_API_KEY"
```

## What next

  - [Models overview](/docs/getting-started/models-overview) — Dashboard catalog with capabilities, pricing, and benchmark data.

