> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-codex-clarify-browser-infrastructure.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Choose a V4 model and configure its reasoning behavior.

Omit `model` to use the default, `gpt-5.6-luna`, or pass a model ID when creating a run.
These common choices appear in the V4 request schema:

| Model         | API string      | BYOK provider |
| ------------- | --------------- | ------------- |
| GPT-5.6 Luna  | `gpt-5.6-luna`  | OpenAI        |
| Claude Opus 5 | `claude-opus-5` | Anthropic     |
| Grok 4.5      | `grok-4.5`      | —             |
| GPT-5.6 Sol   | `gpt-5.6-sol`   | OpenAI        |
| MiniMax M3    | `minimax-m3`    | —             |

See [current pricing](https://browser-use.com/pricing) for model, browser, and
network rates.

See [Thinking levels](/cloud/agent/thinking-levels) for V4 `modelParams` and
the normalized `thinkingLevel` values available in V2 and V3.

<a id="all-supported-v4-model-ids" />

## V4 model IDs in the API schema

The V4 request schema accepts the following model IDs. The Cloud dashboard may
show a smaller curated set; availability can also depend on your account's
rollout and configured provider key.

| Provider    | Model IDs                                                                                  | BYOK provider |
| ----------- | ------------------------------------------------------------------------------------------ | ------------- |
| Anthropic   | `claude-opus-4.7`, `claude-opus-4.8`, `claude-opus-5`, `claude-fable-5`, `claude-sonnet-5` | Anthropic     |
| OpenAI      | `gpt-5.5`, `gpt-5.6`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`                       | OpenAI        |
| Google      | `gemini-3-flash`, `gemini-3.1-pro`, `gemini-3.5-flash`, `gemini-3.6-flash`                 | Google        |
| xAI         | `grok-4.5`                                                                                 | —             |
| Z.ai        | `glm-5.2`                                                                                  | —             |
| Moonshot AI | `kimi-k3`                                                                                  | —             |
| MiniMax     | `minimax-m3`                                                                               | —             |

See [Thinking levels](/cloud/agent/thinking-levels) for the reasoning controls
accepted by each model. Not every model accepts `modelParams`.

<CodeGroup>
  ```python Python theme={null}
  from browser_use_sdk.v4 import BrowserUse

  client = BrowserUse()
  run = client.runs.create(
      "Compare three project-management tools",
      model="gpt-5.6-luna",
  )
  ```

  ```typescript TypeScript theme={null}
  import { BrowserUse } from "browser-use-sdk/v4";

  const client = new BrowserUse();
  const run = await client.runs.create({
    task: "Compare three project-management tools",
    model: "gpt-5.6-luna",
  });
  ```

  ```bash curl theme={null}
  curl https://api.browser-use.com/api/v4/runs \
    -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"task":"Compare three PM tools","model":"gpt-5.6-luna"}'
  ```
</CodeGroup>

## Bring your own key

If BYOK is enabled for your project, add an Anthropic, OpenAI, or Google key
under **Settings → API Keys → Bring Your Own Key**. V4 uses it automatically
for matching models; no request flag is needed. Models from other providers use
Browser Use-managed keys. See [pricing](https://browser-use.com/pricing) for
current BYOK billing.