Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
Changes for VLM launch
f-trycua76b52ece7229
diff --git a/docs/content/docs/agent-sdk/chat-history.mdx b/docs/content/docs/agent-sdk/chat-history.mdxindex e7041c3b8f..e6740fc339 100644--- a/docs/content/docs/agent-sdk/chat-history.mdx+++ b/docs/content/docs/agent-sdk/chat-history.mdx@@ -83,7 +83,7 @@ For long conversations, consider using the `only_n_most_recent_images` parameter```pythonagent = ComputerAgent(- model="anthropic/claude-3-5-sonnet-20241022",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3)diff --git a/docs/content/docs/agent-sdk/custom-tools.mdx b/docs/content/docs/agent-sdk/custom-tools.mdxindex 7e47ebf96c..63d878cba9 100644--- a/docs/content/docs/agent-sdk/custom-tools.mdx+++ b/docs/content/docs/agent-sdk/custom-tools.mdx@@ -16,7 +16,7 @@ def calculate(a: int, b: int) -> int:# Use with agentagent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer, calculate])```@@ -43,7 +43,7 @@ from computer import Computercomputer = Computer(...)agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer, read_file],)```diff --git a/docs/content/docs/agent-sdk/customizing-computeragent.mdx b/docs/content/docs/agent-sdk/customizing-computeragent.mdxindex 82eace7603..a89b926957 100644--- a/docs/content/docs/agent-sdk/customizing-computeragent.mdx+++ b/docs/content/docs/agent-sdk/customizing-computeragent.mdx@@ -67,7 +67,7 @@ Callbacks provide lifecycle hooks to preprocess messages, postprocess outputs, rfrom agent.callbacks import ImageRetentionCallback, TrajectorySaverCallback, BudgetManagerCallbackagent = ComputerAgent(- model="anthropic/claude-3-5-sonnet-20241022",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],callbacks=[ImageRetentionCallback(only_n_most_recent_images=3),diff --git a/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx b/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdxindex 878ab88567..9621e52023 100644--- a/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx+++ b/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx@@ -9,18 +9,6 @@ All agent loops are compatible with any LLM provider supported by LiteLLM.See [Running Models Locally](/agent-sdk/supported-model-providers/local-models) for how to use Hugging Face and MLX models on your own machine.-## UI-TARS-2--Next‑generation UI‑TARS via Cua Router:--- `cua/bytedance/ui-tars-2`--```python-agent = ComputerAgent("cua/bytedance/ui-tars-2", tools=[computer])-async for _ in agent.run("Open a browser and search for Python tutorials"):- pass-```-## Gemini CUAGemini models with computer-use capabilities:diff --git a/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdx b/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdxnew file mode 100644index 0000000000..c2f6cd84cd--- /dev/null+++ b/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdx@@ -0,0 +1,380 @@+---+title: CUA VLM Router+description: Intelligent vision-language model routing with cost optimization and unified access+---++# CUA VLM Router++The **CUA VLM Router** is an intelligent inference API that provides unified access to multiple vision-language model providers through a single API key. It offers cost optimization and detailed observability for production AI applications.++## Overview++Instead of managing multiple API keys and provider-specific code, CUA VLM Router acts as a smart cloud gateway that:++- **Unifies access** to multiple model providers+- **Optimizes costs** through intelligent routing and provider selection+- **Tracks usage** and costs with detailed metadata+- **Provides observability** with routing decisions and attempt logs+- **Managed infrastructure** - no need to manage provider API keys yourself++## Quick Start++### 1. Get Your API Key++Sign up at [cua.ai](https://cua.ai/signin) and get your CUA API key from the dashboard.++### 2. Set Environment Variable++```bash+export CUA_API_KEY="sk_cua-api01_..."+```++### 3. Use with Agent SDK++```python+from agent import ComputerAgent+from computer import Computer++computer = Computer(os_type="linux", provider_type="docker")++agent = ComputerAgent(+ model="cua/anthropic/claude-sonnet-4.5",+ tools=[computer],+ max_trajectory_budget=5.0+)++messages = [{"role": "user", "content": "Take a screenshot and tell me what's on screen"}]++async for result in agent.run(messages):+ for item in result["output"]:+ if item["type"] == "message":+ print(item["content"][0]["text"])+```++## Available Models++The CUA VLM Router currently supports these models:++| Model ID | Provider | Description | Best For |+|----------|----------|-------------|----------|+| `cua/anthropic/claude-sonnet-4.5` | Anthropic | Claude Sonnet 4.5 | General-purpose tasks, recommended |+| `cua/anthropic/claude-haiku-4.5` | Anthropic | Claude Haiku 4.5 | Fast responses, cost-effective |++## How It Works++### Intelligent Routing++When you make a request to CUA VLM Router:++1. **Model Resolution**: Your model ID (e.g., `cua/anthropic/claude-sonnet-4.5`) is resolved to the appropriate provider+2. **Provider Selection**: CUA routes your request to the appropriate model provider+3. **Response**: You receive an OpenAI-compatible response with metadata++## API Reference++### Base URL++```+https://inference.cua.ai/v1+```++### Authentication++All requests require an API key in the Authorization header:++```bash+Authorization: Bearer sk_cua-api01_...+```++### Endpoints++#### List Available Models++```bash+GET /v1/models+```++**Response:**+```json+{+ "data": [+ {+ "id": "anthropic/claude-sonnet-4.5",+ "name": "Claude Sonnet 4.5",+ "object": "model",+ "owned_by": "cua"+ }+ ],+ "object": "list"+}+```++#### Chat Completions++```bash+POST /v1/chat/completions+Content-Type: application/json+```++**Request:**+```json+{+ "model": "anthropic/claude-sonnet-4.5",+ "messages": [+ {"role": "user", "content": "Hello!"}+ ],+ "max_tokens": 100,+ "temperature": 0.7,+ "stream": false+}+```++**Response:**+```json+{+ "id": "gen_...",+ "object": "chat.completion",+ "created": 1763554838,+ "model": "anthropic/claude-sonnet-4.5",+ "choices": [{+ "index": 0,+ "message": {+ "role": "assistant",+ "content": "Hello! How can I help you today?"+ },+ "finish_reason": "stop"+ }],+ "usage": {+ "prompt_tokens": 10,+ "completion_tokens": 12,+ "total_tokens": 22,+ "cost": 0.01,+ "is_byok": true+ }+}+```++#### Streaming++Set `"stream": true` to receive server-sent events:++```bash+curl -X POST https://inference.cua.ai/v1/chat/completions \+ -H "Authorization: Bearer sk_cua-api01_..." \+ -H "Content-Type: application/json" \+ -d '{+ "model": "anthropic/claude-sonnet-4.5",+ "messages": [{"role": "user", "content": "Count to 5"}],+ "stream": true+ }'+```++**Response (SSE format):**+```+data: {"id":"gen_...","choices":[{"delta":{"content":"1"}}],"object":"chat.completion.chunk"}++data: {"id":"gen_...","choices":[{"delta":{"content":"\n2"}}],"object":"chat.completion.chunk"}++data: {"id":"gen_...","choices":[{"delta":{"content":"\n3\n4\n5"}}],"object":"chat.completion.chunk"}++data: {"id":"gen_...","choices":[{"delta":{},"finish_reason":"stop"}],"usage":{...}}+```++#### Check Balance++```bash+GET /v1/balance+```++**Response:**+```json+{+ "balance": 211689.85,+ "currency": "credits"+}+```++## Cost Tracking++CUA VLM Router provides detailed cost information in every response:++### Credit System++Requests are billed in **credits**:+- Credits are deducted from your CUA account balance+- Prices vary by model and usage+- CUA manages all provider API keys and infrastructure++### Response Cost Fields++```json+{+ "usage": {+ "cost": 0.01, // CUA gateway cost in credits+ "market_cost": 0.000065 // Actual upstream API cost+ }+}+```++**Note:** CUA VLM Router is a fully managed cloud service. If you want to use your own provider API keys directly (BYOK), see the [Supported Model Providers](/agent-sdk/supported-model-providers/) page for direct provider access via the agent SDK.++## Response Metadata++CUA VLM Router includes metadata about routing decisions and costs in the response. This information helps with debugging and monitoring your application's model usage.++## Configuration++### Environment Variables++```bash+# Required: Your CUA API key+export CUA_API_KEY="sk_cua-api01_..."++# Optional: Custom endpoint (defaults to https://inference.cua.ai/v1)+export CUA_BASE_URL="https://custom-endpoint.cua.ai/v1"+```++### Python SDK Configuration++```python+from agent import ComputerAgent++# Using environment variables (recommended)+agent = ComputerAgent(model="cua/anthropic/claude-sonnet-4.5")++# Or explicit configuration+agent = ComputerAgent(+ model="cua/anthropic/claude-sonnet-4.5",+ # CUA adapter automatically loads from CUA_API_KEY+)+```++## Benefits Over Direct Provider Access++| Feature | CUA VLM Router | Direct Provider (BYOK) |+|---------|---------------|------------------------|+| **Single API Key** | ✅ One key for all providers | ❌ Multiple keys to manage |+| **Managed Infrastructure** | ✅ No API key management | ❌ Manage multiple provider keys |+| **Usage Tracking** | ✅ Unified dashboard | ❌ Per-provider tracking |+| **Model Switching** | ✅ Change model string only | ❌ Change code + keys |+| **Setup Complexity** | ✅ One environment variable | ❌ Multiple environment variables |++## Error Handling++### Common Error Responses++#### Invalid API Key+```json+{+ "detail": "Insufficient credits. Current balance: 0.00 credits"+}+```++#### Missing Authorization+```json+{+ "detail": "Missing Authorization: Bearer token"+}+```++#### Invalid Model+```json+{+ "detail": "Invalid or unavailable model"+}+```++### Best Practices++1. **Check balance periodically** using `/v1/balance`+2. **Handle rate limits** with exponential backoff+3. **Log generation IDs** for debugging+4. **Set up usage alerts** in your CUA dashboard++## Examples++### Basic Usage++```python+from agent import ComputerAgent+from computer import Computer++computer = Computer(os_type="linux", provider_type="docker")++agent = ComputerAgent(+ model="cua/anthropic/claude-sonnet-4.5",+ tools=[computer]+)++messages = [{"role": "user", "content": "Open Firefox"}]++async for result in agent.run(messages):+ print(result)+```++### Direct API Call (curl)++```bash+curl -X POST https://inference.cua.ai/v1/chat/completions \+ -H "Authorization: Bearer ${CUA_API_KEY}" \+ -H "Content-Type: application/json" \+ -d '{+ "model": "anthropic/claude-sonnet-4.5",+ "messages": [+ {"role": "user", "content": "Explain quantum computing"}+ ],+ "max_tokens": 200+ }'+```++### With Custom Parameters++```python+agent = ComputerAgent(+ model="cua/anthropic/claude-haiku-4.5",+ tools=[computer],+ max_trajectory_budget=10.0,+ temperature=0.7+)+```++## Migration from Direct Provider Access++Switching from direct provider access (BYOK) to CUA VLM Router is simple:++**Before (Direct Provider Access with BYOK):**+```python+# Required: Provider-specific API key+export ANTHROPIC_API_KEY="sk-ant-..."++agent = ComputerAgent(+ model="anthropic/claude-sonnet-4-5-20250929",+ tools=[computer]+)+```++**After (CUA VLM Router - Cloud Service):**+```python+# Required: CUA API key only (no provider keys needed)+export CUA_API_KEY="sk_cua-api01_..."++agent = ComputerAgent(+ model="cua/anthropic/claude-sonnet-4.5", # Add "cua/" prefix+ tools=[computer]+)+```++That's it! Same code structure, just different model format. CUA manages all provider infrastructure and credentials for you.++## Support++- **Documentation**: [cua.ai/docs](https://cua.ai/docs)+- **Discord**: [Join our community](https://discord.com/invite/mVnXXpdE85)+- **Issues**: [GitHub Issues](https://github.com/trycua/cua/issues)++## Next Steps++- Explore [Agent Loops](/agent-sdk/agent-loops) to customize agent behavior+- Learn about [Cost Saving Callbacks](/agent-sdk/callbacks/cost-saving)+- Try [Example Use Cases](/example-usecases/form-filling)+- Review [Supported Model Providers](/agent-sdk/supported-model-providers/) for all optionsdiff --git a/docs/content/docs/agent-sdk/supported-model-providers/index.mdx b/docs/content/docs/agent-sdk/supported-model-providers/index.mdxindex 9177e71207..ed06fd7f98 100644--- a/docs/content/docs/agent-sdk/supported-model-providers/index.mdx+++ b/docs/content/docs/agent-sdk/supported-model-providers/index.mdx@@ -4,7 +4,27 @@ title: Supported Model Providers## Supported Models-### Anthropic Claude (Computer Use API)+### CUA VLM Router (Recommended)++Use CUA's cloud inference API for intelligent routing and cost optimization with a single API key. CUA manages all provider infrastructure and credentials for you.++```python+model="cua/anthropic/claude-sonnet-4.5" # Claude Sonnet 4.5 (recommended)+model="cua/anthropic/claude-haiku-4.5" # Claude Haiku 4.5 (faster)+```++**Benefits:**+- Single API key for multiple providers+- Cost tracking and optimization+- Fully managed infrastructure (no provider keys to manage)++[Learn more about CUA VLM Router →](/agent-sdk/supported-model-providers/cua-vlm-router)++---++### Anthropic Claude (Computer Use API - BYOK)++Direct access to Anthropic's Claude models using your own Anthropic API key (BYOK - Bring Your Own Key).```pythonmodel="anthropic/claude-3-5-sonnet-20241022"@@ -13,14 +33,22 @@ model="anthropic/claude-opus-4-20250514"model="anthropic/claude-sonnet-4-20250514"```-### OpenAI Computer Use Preview+**Setup:** Set `ANTHROPIC_API_KEY` environment variable with your Anthropic API key.++### OpenAI Computer Use Preview (BYOK)++Direct access to OpenAI's computer use models using your own OpenAI API key (BYOK).```pythonmodel="openai/computer-use-preview"```+**Setup:** Set `OPENAI_API_KEY` environment variable with your OpenAI API key.+### UI-TARS (Local or Huggingface Inference)+Run UI-TARS models locally for privacy and offline use.+```pythonmodel="huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B"model="ollama_chat/0000/ui-tars-1.5-7b"@@ -28,6 +56,8 @@ model="ollama_chat/0000/ui-tars-1.5-7b"### Omniparser + Any LLM+Combine Omniparser for UI understanding with any LLM provider.+```pythonmodel="omniparser+ollama_chat/mistral-small3.2"model="omniparser+vertex_ai/gemini-pro"diff --git a/docs/content/docs/computer-sdk/custom-computer-handlers.mdx b/docs/content/docs/computer-sdk/custom-computer-handlers.mdxindex 4559090e24..d166888344 100644--- a/docs/content/docs/computer-sdk/custom-computer-handlers.mdx+++ b/docs/content/docs/computer-sdk/custom-computer-handlers.mdx@@ -34,7 +34,7 @@ You can then use this as a tool for your agent:from agent import ComputerAgentagent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[custom_computer],)@@ -122,7 +122,7 @@ class MyCustomComputer(AsyncComputerHandler):custom_computer = MyCustomComputer()agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[custom_computer],)diff --git a/docs/content/docs/example-usecases/form-filling.mdx b/docs/content/docs/example-usecases/form-filling.mdxindex 7a15cd5f80..817d0dd4dc 100644--- a/docs/content/docs/example-usecases/form-filling.mdx+++ b/docs/content/docs/example-usecases/form-filling.mdx@@ -1,5 +1,5 @@----title: Form Filling+title: PDF to Form Automationdescription: Enhance and Automate Interactions Between Form Filling and Local File Systems---@@ -83,7 +83,7 @@ async def fill_application():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,@@ -189,7 +189,7 @@ async def fill_application():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,@@ -289,7 +289,7 @@ async def fill_application():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,@@ -388,7 +388,7 @@ async def fill_application():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,diff --git a/docs/content/docs/example-usecases/post-event-contact-export.mdx b/docs/content/docs/example-usecases/post-event-contact-export.mdxindex 16131702c5..fc6685d71e 100644--- a/docs/content/docs/example-usecases/post-event-contact-export.mdx+++ b/docs/content/docs/example-usecases/post-event-contact-export.mdx@@ -232,7 +232,7 @@ async def scrape_linkedin_connections():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,diff --git a/docs/content/docs/example-usecases/windows-app-behind-vpn.mdx b/docs/content/docs/example-usecases/windows-app-behind-vpn.mdxindex 7d8d3c8180..82411cc393 100644--- a/docs/content/docs/example-usecases/windows-app-behind-vpn.mdx+++ b/docs/content/docs/example-usecases/windows-app-behind-vpn.mdx@@ -173,7 +173,7 @@ async def automate_hr_workflow():# Configure agent with specialized instructionsagent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,@@ -274,7 +274,7 @@ async def automate_hr_workflow():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,@@ -353,7 +353,7 @@ async def automate_hr_workflow():) as computer:agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],only_n_most_recent_images=3,verbosity=logging.INFO,@@ -476,7 +476,7 @@ For long-running workflows, adjust budget limits:```pythonagent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],max_trajectory_budget=20.0, # Increase for complex workflows# ... other params@@ -535,7 +535,7 @@ Add approval gates for critical operations:```pythonagent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",+ model="cua/anthropic/claude-sonnet-4.5",tools=[computer],# Add human approval callback for sensitive operationscallbacks=[ApprovalCallback(require_approval_for=["payroll", "termination"])]diff --git a/docs/content/docs/get-started/quickstart.mdx b/docs/content/docs/get-started/quickstart.mdxindex 533328353a..0b1ac0d80f 100644--- a/docs/content/docs/get-started/quickstart.mdx+++ b/docs/content/docs/get-started/quickstart.mdx@@ -30,9 +30,23 @@ You can run your Cua computer in the cloud (recommended for easiest setup), loca<Tabs items={['Cloud Sandbox', 'Linux on Docker', 'macOS Sandbox', 'Windows Sandbox']}><Tab value="Cloud Sandbox">- Create and manage cloud sandboxes that run Linux (Ubuntu), Windows, or macOS using either the website or CLI.+ Create and manage cloud sandboxes that run Linux (Ubuntu), Windows, or macOS.- **Option 1: Via CLI (Recommended)**+ **First, create your API key:**++ 1. Go to [cua.ai/signin](https://cua.ai/signin)+ 2. Navigate to **Dashboard > API Keys > New API Key** to create your API key+ 3. **Important:** Copy and save your API key immediately - you won't be able to see it again (you'll need to regenerate if lost)++ **Then, create your sandbox using either option:**++ **Option 1: Via Website**++ 1. Navigate to **Dashboard > Sandboxes > Create Sandbox**+ 2. Create a **Small** sandbox, choosing **Linux**, **Windows**, or **macOS**+ 3. Note your sandbox name++ **Option 2: Via CLI**1. Install the CUA CLI:```bash@@ -51,14 +65,7 @@ You can run your Cua computer in the cloud (recommended for easiest setup), loca3. Note your sandbox name and password from the output- **Option 2: Via Website**-- 1. Go to [cua.ai/signin](https://cua.ai/signin)- 2. Navigate to **Dashboard > Containers > Create Instance**- 3. Create a **Small** sandbox, choosing **Linux**, **Windows**, or **macOS**- 4. Note your sandbox name and API key-- Your Cloud Sandbox will be automatically configured and ready to use with either method.+ Your Cloud Sandbox will be automatically configured and ready to use.</Tab><Tab value="Linux on Docker">@@ -134,14 +141,19 @@ Connect to your Cua computer and perform basic interactions, such as taking scre<Tabs items={['Cloud Sandbox', 'Linux on Docker', 'macOS Sandbox', 'Windows Sandbox', 'Your host desktop']}><Tab value="Cloud Sandbox">+ Set your CUA API key (same key used for model inference):+ ```bash+ export CUA_API_KEY="sk_cua-api01_..."+ ```++ Then connect to your sandbox:```pythonfrom computer import Computercomputer = Computer(os_type="linux", # or "windows" or "macos"provider_type="cloud",- name="your-sandbox-name", # from CLI or website- api_key="your-api-key"+ name="your-sandbox-name" # from CLI or website)await computer.run() # Connect to the sandbox```@@ -226,13 +238,18 @@ Connect to your Cua computer and perform basic interactions, such as taking scre<Tabs items={['Cloud Sandbox', 'Linux on Docker', 'macOS Sandbox', 'Windows Sandbox', 'Your host desktop']}><Tab value="Cloud Sandbox">+ Set your CUA API key (same key used for model inference):+ ```bash+ export CUA_API_KEY="sk_cua-api01_..."+ ```++ Then connect to your sandbox:```typescriptimport { Computer, OSType } from '@trycua/computer';const computer = new Computer({osType: OSType.LINUX, // or OSType.WINDOWS or OSType.MACOS- name: "your-sandbox-name", // from CLI or website- apiKey: "your-api-key"+ name: "your-sandbox-name" // from CLI or website});await computer.run(); // Connect to the sandbox```@@ -322,24 +339,88 @@ Install the Cua agent Python SDK:pip install "cua-agent[all]"```-Then, use the `ComputerAgent` object:+Choose how you want to access vision-language models for your agent:-```python-from agent import ComputerAgent+<Tabs items={['CUA VLM Router', 'BYOK (Bring Your Own Key)']}>+ <Tab value="CUA VLM Router">-agent = ComputerAgent(- model="anthropic/claude-sonnet-4-5-20250929",- tools=[computer],- max_trajectory_budget=5.0-)+ Use CUA's inference API to access multiple model providers with a single API key (same key used for sandbox access). CUA VLM Router provides intelligent routing and cost optimization.-messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]+ **Set your CUA API key:**+ ```bash+ export CUA_API_KEY="sk_cua-api01_..."+ ```-async for result in agent.run(messages):- for item in result["output"]:- if item["type"] == "message":- print(item["content"][0]["text"])-```+ **Use the agent with CUA models:**+ ```python+ from agent import ComputerAgent++ agent = ComputerAgent(+ model="cua/anthropic/claude-sonnet-4.5", # CUA-routed model+ tools=[computer],+ max_trajectory_budget=5.0+ )++ messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]++ async for result in agent.run(messages):+ for item in result["output"]:+ if item["type"] == "message":+ print(item["content"][0]["text"])+ ```++ **Available CUA models:**+ - `cua/anthropic/claude-sonnet-4.5` - Claude Sonnet 4.5 (recommended)+ - `cua/anthropic/claude-haiku-4.5` - Claude Haiku 4.5 (faster)++ **Benefits:**+ - Single API key for multiple providers+ - Cost tracking and optimization+ - No need to manage multiple provider keys++ </Tab>+ <Tab value="BYOK (Bring Your Own Key)">++ Use your own API keys from model providers like Anthropic, OpenAI, or others.++ **Set your provider API key:**+ ```bash+ # For Anthropic+ export ANTHROPIC_API_KEY="sk-ant-..."++ # For OpenAI+ export OPENAI_API_KEY="sk-..."+ ```++ **Use the agent with your provider:**+ ```python+ from agent import ComputerAgent++ agent = ComputerAgent(+ model="anthropic/claude-sonnet-4-5-20250929", # Direct provider model+ tools=[computer],+ max_trajectory_budget=5.0+ )++ messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]++ async for result in agent.run(messages):+ for item in result["output"]:+ if item["type"] == "message":+ print(item["content"][0]["text"])+ ```++ **Supported providers:**+ - `anthropic/claude-*` - Anthropic Claude models+ - `openai/gpt-*` - OpenAI GPT models+ - `openai/o1-*` - OpenAI o1 models+ - `huggingface-local/*` - Local HuggingFace models+ - And many more via LiteLLM++ See [Supported Models](/agent-sdk/supported-model-providers/) for the complete list.++ </Tab>+</Tabs>Learn more about agents in [Agent Loops](/agent-sdk/agent-loops) and available models in [Supported Models](/agent-sdk/supported-model-providers/).