Providers

Configure API keys and settings for AI providers

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

Quick Setup

1. Open Settings (Cmd+, / Ctrl+,)
2. Navigate to Providers
3. Expand any provider and enter your API key
4. 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
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

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
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.

Bedrock Authentication

Bedrock supports multiple authentication methods (tried in order):

1. Bearer Token - Single API key via bearerToken config or AWS_BEARER_TOKEN_BEDROCK env var
2. Explicit Credentials - accessKeyId + secretAccessKey in config
3. 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):

1. Effective model ID - a dated snapshot like claude-sonnet-4-5-20250929
2. Canonical model ID - the model you selected, e.g. claude-sonnet-4-5
3. 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:

1. Explicit per-message override (from thinking level or UI)
2. modelParameters config value
3. 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.