Add enterprise-grade observability, cost tracking, and governance to your Cline AI coding assistant
Create an Integration
Configure Models
Copy the Provider Slug
@openai-dev/gpt-4o
)Run Test Request
button on this step to verify your integration. If you see the error: You do not have enough permissions to execute this request
, you’ll need to create a User API Key for this step to work properly.You can create one here. You should be able to see simple chat request output on this step.@your-provider-slug/your-model-name
Create Default Config
Configure Portkey API Key
Cmd/Ctrl + Shift + P
to open the command paletteCline: Open in new tab
OpenAI Compatible
https://api.portkey.ai/v1
dummy
(since the model is defined in your Portkey config)override_params
is recommended as it allows you to manage all model settings centrally in Portkey, reducing maintenance overhead.OpenAI Compatible
https://api.portkey.ai/v1
@openai-dev/gpt-4o
, @anthropic-test/claude-3-opus-20240229
)Step 1: Implement Budget Controls & Rate Limits
Step 2: Define Model Access Rules
Step 4: Set Routing Configuration
Step 4: Implement Access Controls
Step 5: Deploy & Monitor
How do I update my Provider Budget and Rate limits after creation?
Can I use multiple LLM providers with the same API key?
How do I track costs for different teams?
What happens if a team exceeds their budget limit?
How do I track costs per developer?
What happens if a developer exceeds their budget?
Can I use Cline with local or self-hosted models?
How do I ensure code security with AI assistance?