#OpenAI Provider

Configure Savfox to use OpenAI's GPT models.

#Authentication

#Using Login (Recommended)

savfox login

Follow the interactive prompts to authenticate with OpenAI.

#Using API Key

[auth]
provider = "openai"
api_key = "${OPENAI_API_KEY}"

Or set the environment variable:

export OPENAI_API_KEY=sk-...

#Available Models

#Configuration

[model]
provider_id = "openai"
model = "gpt-4o"

[model.openai]
temperature = 0.7
max_tokens = 4096

#CLI Usage

# Use GPT-4.1
savfox -m gpt-4.1 exec "Refactor this code"

# Use GPT-4.1-mini
savfox -m gpt-4.1-mini exec "Quick task"

# Use o3 for complex reasoning
savfox -m o3 exec "Analyze this architecture"

#Azure OpenAI

For Azure deployments:

[model]
provider_id = "openai"
model = "gpt-4o"

[model.openai]
base_url = "https://your-resource.openai.azure.com"
api_key = "${AZURE_OPENAI_KEY}"
api_version = "2024-02-15-preview"
deployment = "gpt-4o-deployment"

#Rate Limits

OpenAI has rate limits based on your tier:

• Tier 1: 500 RPM
• Tier 2: 5,000 RPM
• Higher tiers available

Savfox handles rate limiting automatically with retries.

#Troubleshooting

#Authentication errors

1. Verify your API key is valid
2. Check if the key has required permissions
3. Ensure the key hasn't been revoked

#Rate limit errors

1. Reduce request frequency
2. Upgrade your OpenAI tier
3. Use a smaller model for non-critical tasks

#Model not found

1. Verify the model name is correct
2. Check if you have access to the model
3. Some models require special access