Perplexity Orchestrator API
One Perplexity API key and one bill for 45+ models from OpenAI, Anthropic, Google, xAI, and open-weight providers, with automatic routing.
Details
- Works with existing OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages code. Change the base URL and API key, and use the model's full ID, such as openai/gpt-6-luna
- Set the model to perplexity/auto and a decision model picks a model for each request, using plain-language route descriptions you write
- You pay each model's published rate, whichever deployment serves the request
- Google, xAI, and open-weight models are open at every usage tier. OpenAI and Anthropic models need Tier 1 or higher, and Claude Opus 5, Opus 5.5, and the Fable models need Tier 2
- It is stateless, so each request must include the full conversation
Best for
Calling many models without managing a separate account and bill for each provider
When to use it
You want requests routed by availability, capacity, and latency, or a different model for each kind of task
Who benefits
Developers building apps that use more than one model
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →