> ## Documentation Index
> Fetch the complete documentation index at: https://docs.llm7.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Available models

> Choose model selectors and discover live model options.

<Warning>
  `pro` is available to Pro subscribers and users with a topped-up balance. Model availability changes over time, so prefer selectors unless you need a specific live model ID.
</Warning>

For most chat applications, use a selector or a live model ID from the Models API:

* `default`: first available general-purpose model
* `fast`: low-latency model for interactive workloads
* `pro`: higher-quality paid model with larger limits or advanced capabilities
* a concrete model ID, such as `gpt-5.4`, when you need to pin routing, behavior, or cost

For image generation, image edits, and video generation, pass a concrete media model ID such as `gpt-image-2` or `gemini-veo31`. Chat selectors such as `default`, `fast`, and `pro` are intended for chat workflows.

```python theme={null}
resp = client.chat.completions.create(
    model="fast",  # or "default", "pro", or a model ID from /v1/models
    messages=[{"role": "user", "content": "Summarize this in one paragraph."}],
)
```

## Live model catalog

Use the Models API when you need exact model IDs, current pricing, context windows, modalities, or capability flags:

```bash theme={null}
curl https://api.llm7.io/v1/models
```

The response is a live catalog. Do not assume a model ID will always be present.

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "id": "gpt-5.4",
      "object": "model",
      "model_type": "chat",
      "tier": "pro",
      "pricing": {
        "input": 0.5,
        "output": 4.5,
        "currency": "USD",
        "unit": "1M tokens"
      },
      "modalities": { "input": ["text"], "output": ["text"] },
      "context_window": { "tokens": 1050000, "chars": null },
      "usage_based_only": true,
      "stream": true,
      "json_mode": true,
      "reasoning": true,
      "tools_calling": true
    }
  ]
}
```

<Card title="Models API" icon="list" href="/guides/models-api">
  Learn how to read tiers, pricing, context windows, modalities, and capability flags.
</Card>

## When to use a specific ID

Use a concrete model ID only when you need to pin behavior for evaluation, routing, or cost controls. Before sending traffic, check the live model catalog and confirm the model supports the feature you need.

For example:

```js theme={null}
const supportsVision = model.modalities?.input?.includes("image");
const supportsImageOutput = model.modalities?.output?.includes("image");
const supportsVideoOutput = model.modalities?.output?.includes("video");
const supportsTools = model.tools_calling === true;
const supportsJson = model.json_mode === true;
```

## Access tiers

`turbo` models are fast models available to anonymous and free-token users. They are a good fit for low-latency and cost-sensitive workloads.

`pro` models are available on Pro subscriptions or paid balances. They may include larger context windows, reasoning, vision, JSON mode, streaming, or tool calling depending on the model record.

See [Limits](/limits) for rate limits and token availability by access type.