> ## Documentation Index
> Fetch the complete documentation index at: https://docs.airun.me/llms.txt
> Use this file to discover all available pages before exploring further.
# Provider Overview
> Understanding AI providers in Andi AIRun
Andi AIRun supports multiple AI providers, allowing you to choose between local models (free, private) and cloud APIs (powerful, scalable).
## Runtimes
AI Runner supports multiple runtimes. Provider availability depends on the runtime:
| Runtime | Flag | Providers |
| ----------- | ---------------- | -------------------------------------------------------------------------------------------------- |
| Claude Code | `--cc` (default) | All Anthropic providers: AWS, Vertex, Azure Foundry, Vercel, Anthropic API, Pro, Ollama, LM Studio |
| Codex CLI | `--codex` | OpenAI API, Azure OpenAI, Ollama, LM Studio, config.toml profiles |
See [Runtimes](/concepts/runtimes) for the full compatibility reference.
## Quick Reference
| Flag | Provider | Type | Notes |
| --------------------- | ----------------- | ------------ | ----------------------------------------------------- |
| `--ollama` / `--ol` | Ollama | Local | Free, no API costs, cloud option |
| `--lmstudio` / `--lm` | LM Studio | Local | MLX models (fast on Apple Silicon) |
| `--aws` | AWS Bedrock | Cloud | Requires AWS credentials |
| `--vertex` | Google Vertex AI | Cloud | Requires GCP project |
| `--apikey` | Anthropic API | Cloud | Direct API access |
| `--azure` | Microsoft Azure | Cloud | Azure Foundry |
| `--vercel` | Vercel AI Gateway | Cloud | Any model: Anthropic, OpenAI, xAI, Google, Meta, more |
| `--pro` | Claude Pro | Subscription | Default if logged in |
Ollama, LM Studio, and Azure work with both runtimes. AWS, Vertex, Vercel, and Pro are Claude Code only. Codex custom providers use `--profile`. See [Runtimes](/concepts/runtimes).
## How Configuration Works
All provider credentials are stored in **one file**: `~/.ai-runner/secrets.sh`
### Initial Setup
This file is created automatically by `./setup.sh` from the `secrets.example.sh` template:
```bash theme={null}
nano ~/.ai-runner/secrets.sh
```
Andi AIRun loads this file at startup. You don't need to set environment variables in your shell profile or `.bashrc` — just add them to `secrets.sh`, and then switch providers freely with `ai --aws`, `ai --vertex`, etc.
You only need to configure the providers you want to use. Configure multiple providers to switch between them when you hit rate limits or want to use different models.
### Session-Scoped Behavior
All provider configurations are session-scoped:
* Changes only affect the active terminal session
* On exit, original settings automatically restore
* Plain `claude` always runs in native state
* Running `claude` in another terminal is unaffected
This means you can safely run `ai --lmstudio` in one terminal while using `claude` normally in another.
## Provider Detection and Defaults
### Automatic Provider Selection
AI Runner first detects which runtime to use (Claude Code or Codex CLI), then selects the appropriate provider. If you don't specify a provider flag, Andi AIRun automatically detects and uses:
1. **Claude Pro** (if logged in with `claude login`)
2. **First configured provider** in secrets.sh
### Setting a Default Provider
You can set a default provider to avoid typing the flag every time:
```bash theme={null}
ai --vercel --model xai/grok-code-fast-1 --set-default
```
Clear the default:
```bash theme={null}
ai --clear-default
```
## Model Tier System
Andi AIRun uses a tiered model system to balance performance and cost:
### Tier Levels
| Tier | Aliases | Use Case | Claude Models |
| --------- | ------------------- | -------------------------------------------------------------------- | ---------------- |
| **Fable** | `--fable`, `--best` | Most demanding reasoning, long-horizon agentic work (Anthropic only) | Claude Fable 5 |
| **High** | `--opus`, `--high` | Complex reasoning, large refactors (default) | Claude Opus 5 |
| **Mid** | `--sonnet`, `--mid` | Cost-conscious coding tasks | Claude Sonnet 5 |
| **Low** | `--haiku`, `--low` | Fast operations, small edits | Claude Haiku 4.5 |
Claude Fable 5 is Anthropic's most capable model, a tier above Opus. It's opt-in (Opus stays the default) and available on Anthropic providers only — on Ollama, LM Studio, and Codex, `--fable`/`--best` falls back to that runtime's highest tier with a notice.
### Usage Examples
```bash theme={null}
# Use high tier for complex reasoning
ai --aws --opus task.md
# Use high tier (default)
ai --aws task.md
# Use low tier for speed and cost savings
ai --vertex --haiku simple-fix.md
```
### Background Model
Andi AIRun uses a "small/fast" model for background operations (like file searches, quick checks). By default, this is set to the **Low** tier model (Haiku).
For local providers (Ollama, LM Studio), the background model defaults to the **same model** as the main tier to avoid costly model swapping.
## Configuring Model Tiers
You can customize model tiers per provider in `secrets.sh`:
### Cloud Providers
```bash theme={null}
# AWS Bedrock
export CLAUDE_MODEL_FABLE_AWS="global.anthropic.claude-fable-5"
export CLAUDE_MODEL_OPUS_AWS="global.anthropic.claude-opus-5"
export CLAUDE_MODEL_SONNET_AWS="global.anthropic.claude-sonnet-5"
export CLAUDE_MODEL_HAIKU_AWS="us.anthropic.claude-haiku-4-5-20251001-v1:0"
# Google Vertex AI
export CLAUDE_MODEL_FABLE_VERTEX="claude-fable-5"
export CLAUDE_MODEL_OPUS_VERTEX="claude-opus-5"
export CLAUDE_MODEL_SONNET_VERTEX="claude-sonnet-5"
export CLAUDE_MODEL_HAIKU_VERTEX="claude-haiku-4-5@20251001"
# Anthropic API (also used by --pro)
export CLAUDE_MODEL_FABLE_ANTHROPIC="claude-fable-5"
export CLAUDE_MODEL_OPUS_ANTHROPIC="claude-opus-5"
export CLAUDE_MODEL_SONNET_ANTHROPIC="claude-sonnet-5"
export CLAUDE_MODEL_HAIKU_ANTHROPIC="claude-haiku-4-5"
# Vercel AI Gateway
export CLAUDE_MODEL_SONNET_VERCEL="xai/grok-code-fast-1"
export CLAUDE_SMALL_FAST_MODEL_VERCEL="xai/grok-code-fast-1"
```
### Local Providers
```bash theme={null}
# Ollama
export OLLAMA_MODEL_HIGH="qwen3-coder"
export OLLAMA_MODEL_MID="qwen3-coder"
export OLLAMA_MODEL_LOW="qwen2.5-coder:7b"
export OLLAMA_SMALL_FAST_MODEL="qwen3-coder" # Same model to avoid swapping
# LM Studio
export LMSTUDIO_MODEL_HIGH="openai/gpt-oss-20b"
export LMSTUDIO_MODEL_MID="openai/gpt-oss-20b"
export LMSTUDIO_MODEL_LOW="ibm/granite-4-micro"
export LMSTUDIO_SMALL_FAST_MODEL="openai/gpt-oss-20b" # Same model
```
## Custom Models
Override the tier system with a specific model:
```bash theme={null}
# Use a specific model
ai --vercel --model xai/grok-code-fast-1
# Use a specific Ollama model
ai --ollama --model glm-5:cloud
# Use a specific AWS model
ai --aws --model global.anthropic.claude-opus-5
```
## Agent Teams
All providers support agent teams (`ai --team`). Coordination uses Claude Code's internal task list and mailbox, not provider-specific features.
Read the Claude Code Agent Teams documentation
## Next Steps
Set up Ollama or LM Studio for free, private AI
Configure AWS, Google, Anthropic, Azure, or Vercel
Learn to switch providers to avoid rate limits