> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-codex-api-v4-agent-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Choose a V4 model and understand its token pricing.

Pass `model` when you create a run. These are the models currently shown in the V4 agent UI:

| Model            | API string         |  Input | Cache read |  Output | Bring your own key |
| ---------------- | ------------------ | -----: | ---------: | ------: | ------------------ |
| Claude Opus 5    | `claude-opus-5`    | \$6.00 |     \$0.60 | \$30.00 | Anthropic          |
| Grok 4.5         | `grok-4.5`         | \$2.40 |     \$0.36 |  \$7.20 | —                  |
| GPT-5.6          | `gpt-5.6`          | \$6.00 |     \$0.60 | \$36.00 | OpenAI             |
| Gemini 3.5 Flash | `gemini-3.5-flash` | \$1.80 |     \$0.18 | \$10.80 | Google             |
| MiniMax M3       | `minimax-m3`       | \$0.36 |    \$0.072 |  \$1.44 | —                  |

Prices are USD per 1 million tokens using Browser Use's provider keys and include the platform markup. Grok 4.5 requests with 200k or more context use its higher long-context rate. Cache prices are for cache reads; cache writes can cost more.

<Tip>
  **MiniMax M3** is the default and the cheapest choice for simple tasks. Use **Claude Opus 5** when maximum reasoning quality matters.
</Tip>

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

  client = AsyncBrowserUse()
  created = await client.runs.create(
      "Compare the top three project-management tools for a 20-person startup",
      model="claude-opus-5",
  )
  run = await client.runs.wait_for_completion(created.id)
  print(run.result)
  ```

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

  const client = new BrowserUse();
  const created = await client.runs.create({
    task: "Compare the top three project-management tools for a 20-person startup",
    model: "claude-opus-5",
  });
  const run = await client.runs.waitForCompletion(created.id);
  console.log(run.result);
  ```

  ```bash curl theme={null}
  curl -X POST https://api.browser-use.com/api/v4/runs \
    -H "X-Browser-Use-API-Key: YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"task": "Compare the top three project-management tools", "model": "claude-opus-5"}'
  ```
</CodeGroup>

## Bring your own key

Add an Anthropic, OpenAI, or Google key under **Settings → API Keys → Bring Your Own Key**. V4 automatically uses a matching project key for that provider; there is no `use_own_key` / `useOwnKey` request flag.

With your own key, you pay the provider directly and Browser Use charges a 0.2× orchestration fee based on provider list token prices. If no matching key is configured, V4 uses Browser Use's provider key and the rates in the table above.

Grok 4.5 and MiniMax M3 currently use Browser Use-managed keys only.