Providers

Mux supports multiple AI providers. The easiest way to configure them is through Settings → Providers (Cmd+, / Ctrl+,).

Quick Setup

Open Settings (Cmd+, / Ctrl+,)
Navigate to Providers
Expand any provider and enter your API key
Start using models from that provider

Most providers only need an API key. The UI handles validation and shows which providers are configured.

Supported Providers

Provider	Models	Get API Key
Anthropic	Claude Opus, Sonnet, Haiku	console.anthropic.com
OpenAI	GPT-5, Codex	platform.openai.com
Google	Gemini Pro, Flash	aistudio.google.com
xAI	Grok	console.x.ai
DeepSeek	DeepSeek Chat, Reasoner	platform.deepseek.com
Moonshot AI	Kimi K3	platform.moonshot.ai
OpenRouter	300+ models	openrouter.ai
Ollama	Local models	ollama.com (no key needed)
Bedrock	Claude via AWS	AWS Console
GitHub Copilot	GPT-4o, Claude Sonnet, etc.	GitHub Copilot
Coder	Models via AI Bridge	Your Coder deployment (Login with Coder, no key needed)

Environment Variables

Providers also read from environment variables as fallback:

Provider	Environment Variable
Anthropic	`ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN`
OpenAI	`OPENAI_API_KEY`
Google	`GOOGLE_GENERATIVE_AI_API_KEY` or `GOOGLE_API_KEY`
xAI	`XAI_API_KEY`
OpenRouter	`OPENROUTER_API_KEY`
DeepSeek	`DEEPSEEK_API_KEY`
Moonshot AI	`MOONSHOT_API_KEY`
github-copilot	`GITHUB_COPILOT_TOKEN`
Bedrock	`AWS_REGION` (credentials via AWS SDK chain)

Advanced: Manual Configuration

For advanced options not exposed in the UI, edit ~/.mux/providers.jsonc directly:

{
  "anthropic": {
    "apiKey": "sk-ant-...",
    "baseUrl": "https://api.anthropic.com", // Optional custom endpoint
  },
  "openrouter": {
    "apiKey": "sk-or-v1-...",
    // Provider routing preferences
    "order": ["Cerebras", "Fireworks"],
    "allow_fallbacks": true,
  },
  "xai": {
    "apiKey": "sk-xai-...",
    // Search orchestration settings
    "searchParameters": { "mode": "auto" },
  },
  "bedrock": {
    "region": "us-east-1",
    // Uses AWS credential chain if no explicit credentials
  },
  "ollama": {
    "baseUrl": "http://your-server:11434/api", // Custom Ollama server
  },
}

Custom OpenAI-compatible providers

Custom OpenAI-compatible providers let you keep the built-in openai provider for OpenAI and Codex, while also adding named local or remote endpoints such as llama.cpp, vLLM, LM Studio, or proxies. Add each endpoint as a top-level provider in ~/.mux/providers.jsonc:

{
  "local-vllm": {
    "providerType": "openai-compatible",
    "displayName": "Local vLLM",
    "baseUrl": "http://localhost:8000/v1",
    "models": ["qwen3-coder"],
  },
}

Option	Required	Description
`providerType`	Yes	Must be `"openai-compatible"` for custom OpenAI-compatible providers.
`baseUrl`	Yes	The OpenAI-compatible API base URL. Most servers require the `/v1` suffix.
`apiKey`	No	Optional API key. Keyless local servers do not need a placeholder key.
`apiKeyFile`	No	Path to a file containing the API key. Supports `~` for home directory.
`displayName`	No	Optional UI label shown instead of the provider ID.
`models`	No	Discovery list shown in the model picker. You can still type any model ID at runtime.

Provider IDs must use lowercase letters, digits, _, and -, and must start with a letter or digit. They must not collide with built-in provider names, and cannot contain ., :, /, or whitespace. Good examples are local-vllm, llama-cpp, and lm-studio.

llama.cpp

{
  "llama-cpp": {
    "providerType": "openai-compatible",
    "displayName": "llama.cpp",
    "baseUrl": "http://localhost:8080/v1",
    "models": ["qwen3-coder"],
  },
}

vLLM

{
  "local-vllm": {
    "providerType": "openai-compatible",
    "displayName": "Local vLLM",
    "baseUrl": "http://localhost:8000/v1",
    "models": ["qwen3-coder"],
  },
}

LM Studio

{
  "lm-studio": {
    "providerType": "openai-compatible",
    "displayName": "LM Studio",
    "baseUrl": "http://localhost:1234/v1",
    "models": ["local-model"],
  },
}

Operational notes:

baseUrl is resolved from the Mux backend process. In desktop mode, this is your local machine. In server mode, the endpoint must be reachable from the server.
Most OpenAI-compatible servers require the /v1 suffix in the URL.
Custom providers use Chat Completions via @ai-sdk/openai-compatible.
Keep the official openai provider for the Responses API, Codex OAuth, and OpenAI service tiers. Custom providers do not inherit those features.
Custom providers are direct-only and do not participate in gateway routing.
You no longer need to set a fake apiKey to point Mux at a keyless local server.

The Coder provider routes requests through a Coder deployment’s AI Gateway (/api/v2/aibridge), so usage is authenticated, governed, and audited by the deployment instead of a personal API key. Deployment prerequisites (admin-side):

The OAuth2 provider experiment: start coderd with --experiments=oauth2 (or CODER_EXPERIMENTS=oauth2)
AI Gateway entitlement and --aibridge-enabled, with at least one provider configured

To connect:

Open Settings → Providers → Coder
Set the Deployment URL (e.g. https://coder.example.com)
Click Login with Coder and approve the request in your browser

Mux registers itself as an OAuth2 client on the deployment (RFC 7591 dynamic client registration), completes an authorization-code + PKCE flow, and stores the resulting tokens in ~/.mux/providers.jsonc. Tokens refresh automatically; Disconnect revokes and clears them. After login, Mux discovers the deployment’s configured AI Gateway providers and their model catalogs, listing models as coder:<provider>/<model> (e.g. coder:anthropic/<model>, coder:my-openai/<model>). Each provider’s type (anthropic, openai, bedrock, openai-compat, …) decides the wire protocol Mux speaks to its gateway route. Use the Refresh models button (or the “Settings: Refresh Coder Models” command) to re-discover without a re-login. You can also add model IDs manually under the provider’s model list; manual edits are preserved across re-logins and catalog refreshes: added entries stay listed, and removed catalog entries stay removed. Listing the deployment’s providers requires an admin-level API on some deployments; when it is unavailable Mux probes the default provider names instead. If your deployment uses custom-named provider instances that Mux cannot discover, declare them by hand in ~/.mux/providers.jsonc:

{
  "coder": {
    "additionalProviders": [{ "name": "llm-proxy", "type": "openai-compat" }],
    "models": ["llm-proxy/llama-3.3-70b"],
  },
}

Login is available from the desktop app or a locally hosted Mux server. On a remote Mux server the OAuth callback cannot reach your browser’s machine (Coder does not support the device-authorization grant), so login is disabled there.

Bedrock Authentication

Bedrock supports multiple authentication methods (tried in order):

Bearer Token - Single API key via bearerToken config or AWS_BEARER_TOKEN_BEDROCK env var
Explicit Credentials - accessKeyId + secretAccessKey in config
AWS Credential Chain - Automatic resolution from environment, ~/.aws/credentials, SSO, EC2/ECS roles

If you’re already authenticated with AWS CLI (aws sso login), Mux uses those credentials automatically.

OpenRouter Provider Routing

Control which infrastructure providers handle your requests:

order: Priority list of providers (e.g., ["Cerebras", "Fireworks"])
allow_fallbacks: Whether to try other providers if preferred ones are unavailable
only / ignore: Restrict or exclude specific providers
data_collection: "allow" or "deny" for training data policies

See OpenRouter Provider Routing docs for details.

xAI Search Orchestration

Grok models support live web search. Mux enables this by default with mode: "auto". Customize via searchParameters for regional focus, time filters, or to disable search.

Model Parameter Overrides

Set per-model defaults for parameters like temperature, token limits, and sampling by adding a modelParameters section under any provider:

{
  "anthropic": {
    "apiKey": "sk-ant-...",
    "modelParameters": {
      // Override for a specific model
      "claude-sonnet-4-5": {
        "temperature": 0.7,
        "max_output_tokens": 16384,
      },
      // Wildcard default for all Anthropic models
      "*": {
        "max_output_tokens": 8192,
      },
    },
  },
}

Supported parameters

Parameter	Range	Description
`temperature`	0–2	Randomness of responses
`top_p`	0–1	Nucleus sampling threshold
`top_k`	positive integer	Top-K sampling
`max_output_tokens`	positive integer	Maximum response length
`seed`	integer	Deterministic generation seed
`frequency_penalty`	number	Penalize repeated tokens
`presence_penalty`	number	Penalize tokens already present

Any unrecognized key is passed through as a provider-specific option (for example, OpenRouter routing hints).

Resolution order

When multiple entries could match, the first match wins (no merging across tiers):

Effective model ID - a dated snapshot like claude-sonnet-4-5-20250929
Canonical model ID - the model you selected, e.g. claude-sonnet-4-5
Wildcard "*" - catch-all for that provider

For example, if you configure both "claude-sonnet-4-5" and "*" with different temperatures, requesting claude-sonnet-4-5 uses the specific entry - the wildcard is not merged in.

Priority with other settings

For max_output_tokens specifically, the priority chain is:

Explicit per-message override (from thinking level or UI)
modelParameters config value
Model’s built-in default

This means model parameters act as a default - they never override explicit per-message choices.

Some providers require specific parameter values when extended thinking is enabled. For example, Anthropic requires temperature: 1 with thinking. Setting a different temperature in modelParameters may cause API errors when thinking is active.

Getting Started

Workspaces

Agents

Configuration

Guides

Integrations

Reference

Providers

Quick Setup

Supported Providers

Environment Variables

Advanced: Manual Configuration

Custom OpenAI-compatible providers

llama.cpp

vLLM

LM Studio

Bedrock Authentication

OpenRouter Provider Routing

xAI Search Orchestration

Model Parameter Overrides

Supported parameters

Resolution order

Priority with other settings

​Quick Setup

​Supported Providers

​Environment Variables

​Advanced: Manual Configuration

​Custom OpenAI-compatible providers

​llama.cpp

​vLLM

​LM Studio

​Coder (Login with Coder)

​Bedrock Authentication

​OpenRouter Provider Routing

​xAI Search Orchestration

​Model Parameter Overrides

​Supported parameters

​Resolution order

​Priority with other settings

Quick Setup

Supported Providers

Environment Variables

Advanced: Manual Configuration

Custom OpenAI-compatible providers

llama.cpp

vLLM

LM Studio

Coder (Login with Coder)

Bedrock Authentication

OpenRouter Provider Routing

xAI Search Orchestration

Model Parameter Overrides

Supported parameters

Resolution order

Priority with other settings