Claude Cowork Now Runs Any LLM. Test It Free.

OpenAI, Gemma, Kimi K2, or run locally. Free via OpenRouter. Anthropic shipped it quietly.

Apr 23, 2026

You can now run Claude Cowork and Code in Claude Desktop against any LLM.

GPT-5, Grok, Gemini, open-weight models via OpenRouter, a local model on your laptop, or your enterprise gateway (Bedrock, Vertex, Foundry).

Claude Cowork with GPT-5, Grok, Gemini, open-weight models via OpenRouter, a local model

Anthropic shipped it quietly. No announcement. No blog post. Just technical docs. I discovered it by accident. 20+ hours later, still zero official word.

Paweł Huryn@PawelHuryn

Anthropic has quietly shipped third-party inference for Cowork and Code in Claude Desktop. This should work with local models or OpenRouter via LiteLLM proxy. Is it just me?

7:46 PM · Apr 22, 2026 · 530K Views

46 Replies · 68 Reposts · 947 Likes

1. What It Actually Is

Built for enterprises and individuals. Same config panel, same admin controls.

If your organization uses Amazon Bedrock, Google Cloud Vertex AI, Azure AI Foundry, or an LLM gateway to access Claude, you can deploy Claude Cowork to run on the same infrastructure.

This is a research preview. The official docs cover three paths:

regulated industries
companies running Claude through their own gateway
individuals on pilot/evaluation setups

Any individual can install it today.

Every admin control (per-user token caps, MCP allowlist, OpenTelemetry, block auto-updates, remove built-in tools) ships on all three paths.

OpenRouter counts as an LLM gateway. Anthropic doesn’t list it in the docs, but I tested that it works. Confirmed by the OpenRouter CEO:

Alex Atallah@alexatallah

OpenRouter now works in Claude Cowork!

Paweł Huryn @PawelHuryn

Anthropic has quietly shipped third-party inference for Cowork and Code in Claude Desktop. This should work with local models or OpenRouter via LiteLLM proxy. Is it just me?

2:43 AM · Apr 23, 2026 · 43.9K Views

11 Replies · 7 Reposts · 231 Likes

Brief summary:

Foundry: during this research preview, Claude on Foundry still runs on Anthropic’s infrastructure. Bedrock and Vertex are the paths with full provider-side data residency.

2. Who This Is For

Two audiences. Same config, different endpoint.

Individuals:

Hitting Max plan weekly limits
Want to try Cowork without paying $100 or $200 a month
Running a local model on code you can’t send to any API

Enterprise:

Already on Bedrock, Vertex, or Foundry. Keep the harness inside your existing compliance boundary
Security approves your cloud provider but not Anthropic direct
Need team-wide admin controls (token caps, MCP allowlist, OpenTelemetry)

Side note: Find this helpful? Here are some other Claude posts you may have missed:

Subscribe and upgrade your account for the full experience:

3. Enable & Configure

3.1 Connect to OpenRouter

No proxy needed. Point Claude Desktop straight at OpenRouter.

Menu → Developer → Configure Third-Party Inference
Set:
1. Connection: Gateway
2. Gateway base URL: https://openrouter.ai/api
3. Gateway API key: your OpenRouter key
4. Gateway auth scheme: x-api-key
5. In the Sandbox & workspace configure "Allowed egress hosts" so that your agents can access the web. For example (all sites):
Click: Apply locally → Relaunch now
Log out, then Continue with Gateway:
You’ll see “Setting up Claude’s workspace...” You can start chatting:

Select an OpenRouter model. The free one that works for me: tencent/hy3-preview:free

Local models work the same way through an OpenAI-compatible proxy (LiteLLM, Ollama’s OpenAI endpoint). I’ll cover local setup in a separate post.

3.2 Import Anthropic skills

OpenRouter setups ship with Customize → Skills empty. Install the official Claude Desktop skills (docx, pdf, pptx, xlsx, skill-creator) manually.

Download the skills repo as .zip: https://github.com/anthropics/skills/tree/main/skills
Extract skills-main.zip, go inside
Zip the skill folders you want individually (e.g., docx folder → docx.zip)
In Claude Desktop: Customize → Skills → Create skill → Upload a skill. Upload each .zip

Only import the ones you need. Skills take context window space even when not fully loaded.

3.3 Import Anthropic plugins

Same pattern. Two repos worth pulling from:

Knowledge-work plugins (marketing, product-management, legal, finance): https://github.com/anthropics/knowledge-work-plugins
Code tab plugins: https://github.com/anthropics/claude-plugins-official

Steps:

Download the repo as .zip
Extract, go inside
Zip the plugin folders you want (e.g., product-management → product-management.zip)
In Claude Desktop: Customize → Personal plugins → + → Create plugin → Upload plugin

Cap it at 2–3 plugins. Often 0 is right.

3.4 Configure MCP servers

MCP servers are local. Add them under Settings → Developer.

Configure MCP servers in Claude Cowork on 3P Gateway

They write to a dedicated claude_desktop_config.json file (if you don’t see that option see 4. Troubleshooting).

You can find servers at github.com/modelcontextprotocol/servers (official).

Example: Atlassian (Jira + Confluence) via the community mcp-atlassian server:

{
  "mcpServers": {
    "atlassian": {
      "command": "uvx",
      "args": ["mcp-atlassian"],
      "env": {
        "JIRA_URL": "https://your-domain.atlassian.net",
        "JIRA_USERNAME": "your-email@example.com",
        "JIRA_API_TOKEN": "your_api_token"
      }
    }
  }
}

3.5 Search

OpenRouter doesn’t support Anthropic’s native web search. Three ways around it:

Replace it with an MCP. Add WebSearch to disabledBuiltinTools so that the agent is not confused and install the Brave MCP server (2,000 free requests/month, or $3 per 1,000).

Add this MCP:

{
  "mcpServers": {
    "brave-search": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-brave-search"],
      "env": { "BRAVE_API_KEY": "YOUR_API_KEY_HERE" }
    }
  }
}

Switch provider to Vertex AI or Microsoft Foundry. Both support native web search. Amazon Bedrock doesn’t yet.
Wait. OpenRouter could route Anthropic’s web_search tool to Perplexity or similar - not shipped yet.

Side Note: On May 9, we’re launching Hands-On Claude Code Certification. In 4 weeks you will learn everything to ship full agentic products — UI, agentic harness, evals, guardrails, and ops — with Claude Code. Real apps, not demos.

Secure your spot (40% off)

Most students expense this through their companies.

4. Troubleshooting

Can’t see “Configure Third-Party Inference” in Menu → Developer

Update Claude Desktop and restart. Then enable developer mode: Help → Troubleshooting → Enable Developer Mode.

Users on corporate/Team plans have reported the setting is still missing even with developer mode on. It may be plan-gated or A/B rolled.

Can’t see “Local MCP servers” in Cowork on 3P

Update Claude Desktop and restart. Then enable developer mode: Help → Troubleshooting → Enable Developer Mode.

Connectors show as “Unavailable”

Not a bug. Third-party inference means running without Anthropic’s infrastructure. Connectors depend on that layer. Use an MCP server instead (See 3.4).

Tool calling is flaky on non-Claude models

Models vary. Some handle MCP calls cleanly; others break on multi-step agentic flows. The best I’ve tested: https://www.productcompass.pm/i/193559427/api-pay-per-token-choose-your-model

Code tab settings don’t match Cowork settings

Acknowledged in Anthropic’s docs: some Cowork on 3P config keys don’t propagate identically to Code-tab sessions yet.

5. What This Signals

Look at what ships in Configure Third-Party Inference:

Max tokens per window (per-user soft cap)
Allow user-added MCP servers
OpenTelemetry collector endpoint
Block auto-updates
Remove built-in tools from Cowork

None of those matter to a solo user. They’re admin controls. Paired with Bedrock, Vertex, and Foundry support, Anthropic’s official framing is explicit:

Cowork on 3P is designed for organizations whose security, regulatory, or contractual requirements prevent them from sending data to Anthropic’s first-party infrastructure.

Claude Desktop is becoming a managed agent platform. The harness (Code, Cowork, skills, plugins, MCP, sub-agents) is what Anthropic wants to be the default, regardless of which model sits behind it.

The individual path is documented, not an accident. On my Max plan, the full config panel shows up. Anthropic's docs don't explicitly say end users get this; the install section just tells you to "enter the values supplied by your administrator." But on a personal install, with no administrator in the picture, those fields sit there for you to set.

Docs:

Download and install Claude Desktop. Start with a free OpenRouter model. No $200/mo subscription required.

We’ve covered the Claude ecosystem in the previous posts and recorded meetings available to the premium members.

Thanks for Reading The Product Compass

It’s amazing to learn and grow together.

I’m uploading two new recordings, Building Agents with Claude Code and Context Window Optimization, tomorrow.

Take care,
Paweł

The Product Compass

Discussion about this post

Ready for more?