Configure AI Providers

Configure API Access

To run pipelines with LLMs, you need to configure API access. You have three options - choose what works best for you:

Option 1: Pipelex Gateway — Easiest and most Powerful for Getting Started

Get free credits for testing and development with a single API key for LLMs, document extraction, and image generation across all major providers (OpenAI, Anthropic, Google, Azure, open-source, and more). New models added constantly.

Benefits:

No credit card required
Access to OpenAI, Anthropic Claude, Google Gemini, xAI Grok, and more
New models added constantly
Perfect for development and testing
Single API key for all models

Setup:

Get your API key at app.pipelex.com
Create a .env file in your project root:
```
PIPELEX_GATEWAY_API_KEY=your-key-here
```
Run pipelex init and accept the Gateway terms of service when prompted.

That's it! Your pipelines can now access any supported LLM. See Gateway Available Models for the full list.

Terms of Service & Telemetry

When using Pipelex Gateway, you'll be prompted to accept our terms of service. By using the Gateway, identified telemetry is automatically enabled (tied to your hashed API key) to help us monitor service quality and enforce fair usage.

We collect only technical data (model names, token counts, latency, error rates). We do NOT collect your prompts, completions, or business data. See Telemetry for details and trade-offs, and our Privacy Policy for more.

Migration from pipelex_inference

If you were using the deprecated pipelex_inference backend, migrate to pipelex_gateway:

Get your new Gateway API key at app.pipelex.com
Update your .env: set PIPELEX_GATEWAY_API_KEY with your new key
Run pipelex init and accept the Gateway terms

The pipelex_inference backend is deprecated and will be removed in a future release.

Option 2: Bring Your Own API Keys

Use your existing API keys from LLM providers. This is ideal if you:

Already have API keys from providers
Need to use specific accounts for billing
Have negotiated rates or enterprise agreements
Prefer not to send any telemetry to Pipelex servers

Setup:

Create a .env file in your project root with your provider keys:

# OpenAI
OPENAI_API_KEY=sk-...

# Anthropic
ANTHROPIC_API_KEY=sk-ant-...

# Google
GOOGLE_API_KEY=...

# Mistral
MISTRAL_API_KEY=...

# FAL (for image generation)
FAL_API_KEY=...

# XAI
XAI_API_KEY=...

# Azure OpenAI
AZURE_API_KEY=...
AZURE_API_BASE=...
AZURE_API_VERSION=...

# Amazon Bedrock
AWS_ACCESS_KEY_ID=...
AWS_SECRET_ACCESS_KEY=...
AWS_REGION=...

You only need to add keys for the providers you plan to use.

Enable Your Providers:

When using your own keys, enable the corresponding backends:

Initialize configuration:
```
pipelex init config
```

Edit .pipelex/inference/backends.toml:

[google]
enabled = true

[openai]
enabled = true

# Enable any providers you have keys for

See Inference Backend Configuration for all options.

Option 3: Local AI (No API Keys Required)

Run AI models locally without any API keys. This is perfect if you:

Want complete privacy and control
Have capable hardware (GPU recommended)
Need offline capabilities
Want to avoid API costs

Supported Local Options:

Ollama (Recommended):

Install Ollama
Pull a model: ollama pull llama2
No API key needed! Configure Ollama backend in .pipelex/inference/backends.toml

Other Local Providers:

vLLM: High-performance inference server
LM Studio: User-friendly local model interface
llama.cpp: Lightweight C++ inference

Configure these in .pipelex/inference/backends.toml. See our Inference Backend Configuration for details.

Backend Configuration Files

To set up Pipelex configuration files, run:

pipelex init config

This creates a .pipelex/ directory with:

.pipelex/
├── pipelex.toml              # Feature flags, logging, cost reporting
├── telemetry.toml            # Custom telemetry configuration
└── inference/                # LLM configuration and model presets
    ├── backends.toml         # Enable/disable model providers
    ├── deck/
    │   └── base_deck.toml    # LLM presets and aliases
    └── routing_profiles.toml # Model routing configuration

Learn more in our Inference Backend Configuration guide.

Next Steps

Now that you have your backend configured:

Organize your project: Project Organization
Learn the concepts: Writing Workflows Tutorial

Explore examples: Cookbook Repository
Deep dive: Build Reliable AI Workflows

Advanced Configuration

For detailed backend configuration options, see Inference Backend Configuration.