Skip to main content
Cloud providers offer powerful AI models through APIs, with pay-as-you-go pricing and no local hardware requirements.

​
AWS Bedrock

AWS Bedrock provides Claude models through Amazon’s infrastructure.

​
Configuration

Add to ~/.ai-runner/secrets.sh: 
export AWS_PROFILE="your-profile-name"
export AWS_REGION="us-west-2"

​
Authentication Methods

AWS Bedrock supports three authentication methods: 
export AWS_BEARER_TOKEN_BEDROCK="your-bedrock-api-key"
export AWS_REGION="us-west-2"

​
2. AWS Access Keys

export AWS_ACCESS_KEY_ID="your_access_key"
export AWS_SECRET_ACCESS_KEY="your_secret_key"
export AWS_SESSION_TOKEN="your_session_token"  # Optional
export AWS_REGION="us-west-2"

​
3. AWS Profile

export AWS_PROFILE="your-profile-name"
export AWS_REGION="us-west-2"

​
Usage

# Use default tier (Opus)
ai --aws

# Use specific tier
ai --aws --opus task.md
ai --aws --sonnet task.md
ai --aws --haiku quick-fix.md
--fable/--best on Bedrock needs a one-time data-sharing enablement. Fable 5 is a Mythos-class Covered Model: Anthropic retains inputs/outputs for 30 days with human review on every platform that offers it (direct API, Pro, Bedrock, Vertex, Azure) — this is a property of the model, not of Bedrock. Bedrock’s default mode doesn’t share data with the provider, so it won’t serve Fable until you enable provider data sharing; until then requests fail mid-session with 400 data retention mode 'default' is not available for this model.There is no console UI — enable it at the account level via the Data Retention API:
curl -X PUT https://bedrock-mantle.<region>.api.aws/v1/data_retention \
  -H "x-api-key: <your-bedrock-api-key>" \
  -H "Content-Type: application/json" \
  -d '{ "mode": "provider_data_share" }'
Bedrock-specific caveat: once enabled, Fable traffic leaves AWS’s data/security boundary (it goes to Anthropic). --apikey and --azure don’t need this step — not because they retain less, but because their standard config already shares with Anthropic. The only way to avoid 30-day retention entirely is to not use Fable (stay on --opus). See Anthropic’s data-retention policy for Mythos-class models.

​
Custom Models

Override default models in secrets.sh: 
export CLAUDE_MODEL_FABLE_AWS="global.anthropic.claude-fable-5"
export CLAUDE_MODEL_OPUS_AWS="global.anthropic.claude-opus-4-8"
export CLAUDE_MODEL_SONNET_AWS="global.anthropic.claude-sonnet-4-6"
export CLAUDE_MODEL_HAIKU_AWS="us.anthropic.claude-haiku-4-5-20251001-v1:0"
export CLAUDE_SMALL_FAST_MODEL_AWS="us.anthropic.claude-haiku-4-5-20251001-v1:0"

AWS Bedrock Setup

Read the complete AWS Bedrock setup guide

​
Google Vertex AI

Google Vertex AI provides Claude models through Google Cloud Platform.

​
Configuration

Add to ~/.ai-runner/secrets.sh: 
export ANTHROPIC_VERTEX_PROJECT_ID="your-gcp-project-id"
export CLOUD_ML_REGION="global"

​
Authentication

Vertex AI supports three authentication methods (in precedence order):

​
1. Service Account Key File

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"

​
2. Application Default Credentials

gcloud auth application-default login

​
3. User Credentials

gcloud auth login

​
Prerequisites

  1. Install Google Cloud SDK: https://cloud.google.com/sdk/docs/install
  2. Authenticate with one of the methods above
  3. Enable Claude models in Vertex AI Model Garden

​
Usage

# Use default tier (Opus)
ai --vertex

# Use specific tier
ai --vertex --opus task.md
ai --vertex --sonnet task.md
ai --vertex --haiku quick-fix.md
--fable/--best on Vertex needs a one-time data-sharing enablement. Fable 5 is a Mythos-class Covered Model (30-day retention + human review on every platform that offers it — a model property, not Vertex-specific). Vertex won’t serve it until you enable data sharing for the anthropic publisher; until then requests fail with 403 ... requires data sharing to be enabled for publisher 'anthropic'.Enable it (project-level), either way:
  • Console (simplest): open the Claude Fable 5 model card in Vertex AI Model Garden and accept the data-sharing terms.
  • API: call setPublisherModelConfig, setting the field named in your 403 (data_sharing_enabled_provider) to anthropic: 
    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://<region>-aiplatform.googleapis.com/v1beta1/projects/<project-id>/locations/<region>/publishers/anthropic/models/claude-fable-5:setPublisherModelConfig" \
  -d '{ "publisherModelConfig": { "data_sharing_enabled_provider": "anthropic" } }'
--apikey and --azure don’t need this step (their standard config already shares with Anthropic). To avoid 30-day retention entirely, don’t use Fable — stay on --opus. See Claude on Vertex AI.

​
Custom Models

Override default models in secrets.sh: 
export CLAUDE_MODEL_FABLE_VERTEX="claude-fable-5"
export CLAUDE_MODEL_OPUS_VERTEX="claude-opus-4-8"
export CLAUDE_MODEL_SONNET_VERTEX="claude-sonnet-4-6"
export CLAUDE_MODEL_HAIKU_VERTEX="claude-haiku-4-5@20251001"
export CLAUDE_SMALL_FAST_MODEL_VERTEX="claude-haiku-4-5@20251001"

​
Regional Overrides

For specific model regional availability: 
export VERTEX_REGION_CLAUDE_4_6_OPUS="us-east5"
export VERTEX_REGION_CLAUDE_4_6_SONNET="us-east5"

Vertex AI Setup

Read the complete Vertex AI setup guide

​
Anthropic API

Direct API access to Anthropic’s Claude models.

​
Configuration

Add to ~/.ai-runner/secrets.sh: 
export ANTHROPIC_API_KEY="sk-ant-..."

​
Getting an API Key

  1. Sign up at console.anthropic.com
  2. Navigate to API Keys
  3. Create a new API key
  4. Add it to your secrets.sh

​
Usage

# Use default tier (Opus)
ai --apikey

# Use specific tier
ai --apikey --opus task.md
ai --apikey --sonnet task.md
ai --apikey --haiku quick-fix.md

​
Custom Models

Override default models in secrets.sh: 
export CLAUDE_MODEL_FABLE_ANTHROPIC="claude-fable-5"
export CLAUDE_MODEL_OPUS_ANTHROPIC="claude-opus-4-8"
export CLAUDE_MODEL_SONNET_ANTHROPIC="claude-sonnet-4-6"
export CLAUDE_MODEL_HAIKU_ANTHROPIC="claude-haiku-4-5"
export CLAUDE_SMALL_FAST_MODEL_ANTHROPIC="claude-haiku-4-5"
If you’re also logged into Claude Pro, you’ll see an “Auth conflict” warning from Claude Code. This is normal - Claude Code will use the API key for billing. The warning is just informational.

Anthropic API Docs

Read the Anthropic API documentation

​
Microsoft Azure

Microsoft Foundry on Azure provides Claude models through Azure.

​
Configuration

Add to ~/.ai-runner/secrets.sh: 
export ANTHROPIC_FOUNDRY_API_KEY="your-azure-api-key"
export ANTHROPIC_FOUNDRY_RESOURCE="your-resource-name"
Or provide the full URL: 
export ANTHROPIC_FOUNDRY_BASE_URL="https://your-resource-name.services.ai.azure.com"

​
Authentication Methods

export ANTHROPIC_FOUNDRY_API_KEY="your-azure-api-key"
export ANTHROPIC_FOUNDRY_RESOURCE="your-resource-name"

​
2. Azure Default Credentials

az login
export ANTHROPIC_FOUNDRY_RESOURCE="your-resource-name"

​
Usage

# Use default tier (Opus)
ai --azure

# Use specific tier
ai --azure --opus task.md
ai --azure --sonnet task.md
ai --azure --haiku quick-fix.md

​
Custom Models

Azure model names are deployment names (user-defined). Override in secrets.sh: 
export CLAUDE_MODEL_FABLE_AZURE="claude-fable-5"
export CLAUDE_MODEL_OPUS_AZURE="claude-opus-4-8"
export CLAUDE_MODEL_SONNET_AZURE="claude-sonnet-4-6"
export CLAUDE_MODEL_HAIKU_AZURE="claude-haiku-4-5"
export CLAUDE_SMALL_FAST_MODEL_AZURE="claude-haiku-4-5"

Microsoft Foundry Setup

Read the complete Microsoft Foundry setup guide

​
Vercel AI Gateway

Vercel AI Gateway provides unified access to 100+ models from multiple providers.

​
Configuration

Add to ~/.ai-runner/secrets.sh: 
export VERCEL_AI_GATEWAY_TOKEN="vck_..."
export VERCEL_AI_GATEWAY_URL="https://ai-gateway.vercel.sh"  # Optional

​
Getting a Token

  1. Visit vercel.com/dashboard/~/ai
  2. Create a new AI Gateway token
  3. Add it to your secrets.sh

​
Usage with Claude Models

# Use default tier (Opus)
ai --vercel

# Use specific tier
ai --vercel --opus task.md
ai --vercel --sonnet task.md
ai --vercel --haiku quick-fix.md

​
Use Any Model

Vercel AI Gateway supports 100+ models from OpenAI, xAI, Google, Meta, Anthropic, Mistral, DeepSeek, and more — all through one API. Use --model provider/model to run Claude Code with any supported model: 
ai --vercel --model xai/grok-code-fast-1         # xAI coding model
ai --vercel --model openai/gpt-5.2-codex         # OpenAI coding model
ai --vercel --model google/gemini-3-pro-preview  # Google reasoning model
ai --vercel --model alibaba/qwen3-coder          # Alibaba coding model
ai --vercel --model zai/glm-5                    # Zhipu AI GLM-5 198K context

​
Example Coding Models

Model IDProviderDescription
xai/grok-code-fast-1xAIFast coding model
openai/gpt-5.2-codexOpenAICoding-optimized GPT (also openai/gpt-5.3-codex)
google/gemini-3-pro-previewGoogleLatest reasoning model
alibaba/qwen3-coderAlibabaOpen-source coding model
zai/glm-5Zhipu AIGLM-5, 198K context, MIT license

Browse All Models

View all available models on Vercel AI Gateway

​
Configuration for Non-Anthropic Models

When using non-Anthropic models, configure defaults in secrets.sh: 
# Use a non-Anthropic model as default for Vercel
export CLAUDE_MODEL_SONNET_VERCEL="xai/grok-code-fast-1"

# Set a specific background/small-fast model
export CLAUDE_SMALL_FAST_MODEL_VERCEL="xai/grok-code-fast-1"

# Fable 5 (--fable/--best) slug; override if Vercel's catalog differs
export CLAUDE_MODEL_FABLE_VERCEL="anthropic/claude-fable-5"
Automatic small/fast model: When you use --model with a non-Anthropic model (e.g., xai/grok-code-fast-1), the background model is automatically set to the same model. This avoids mixing providers (e.g., xAI for main work + Anthropic for background). For Anthropic models on Vercel, the background model defaults to Haiku as usual.

​
Set as Default Provider

ai --vercel --model xai/grok-code-fast-1 --set-default
ai --clear-default

​
Claude Pro

Uses your Claude Pro/Max subscription. No API keys needed.

​
Prerequisites

  • Claude Code installed
  • Logged in with Claude subscription: 
    claude login

​
Usage

# Use default tier (Opus)
ai --pro

# Use specific tier
ai --pro --opus task.md
ai --pro --sonnet task.md
ai --pro --haiku quick-fix.md
This is the default provider if you’re logged into Claude Code with a subscription.
--fable/--best (Claude Fable 5) works with --pro, but availability depends on your Claude subscription plan. If your plan doesn’t include Fable, use an API provider (--apikey, --aws, --vertex) instead.
Claude Pro has rate limits. When you hit a limit, switch to an API provider with --resume to continue your work.

​
Provider Comparison

ProviderSetup ComplexityCost ModelModel SelectionBest For
OllamaEasyFreeOpen-source modelsLocal, privacy, cloud fallback
LM StudioEasyFreeCustom modelsApple Silicon, custom models
AWS BedrockMediumPay-per-useClaude modelsAWS integration
Vertex AIMediumPay-per-useClaude modelsGCP integration
Anthropic APIEasyPay-per-useClaude modelsDirect access
AzureMediumPay-per-useClaude modelsAzure integration
VercelEasyPay-per-use100+ modelsMulti-provider access
Claude ProEasiestSubscriptionClaude modelsRate limits exist

​
Next Steps

Provider Overview

Learn about the provider system

Switching Providers

Switch providers to avoid rate limits