Feature Roadmap
API Roadmap
Upcoming features and improvements for the Perplexity API designed to enhance your development experience.
Our roadmap is shaped by our users - have a feature in mind? Submit your suggestion here and help us build the future of AI together.
We’re prioritizing significant improvements to Sonar Deep Research to better support complex and long-running queries.
Key features include:
- Poll-for-Completion Mechanism: Users will no longer need to keep the network connection open while awaiting a response. Instead, you can poll the API for completion status.
- Enhanced performance and reliability for deep research tasks.
These updates will make Sonar Deep Research more efficient and user-friendly for advanced use cases.
Expanding your ability to access and process information:
- Search across various file types
- Integration with external data sources
- Parity with enterprise connector capabilities
This feature will allow your applications to tap into a broader range of data sources for more comprehensive insights.
We’re expanding our structured outputs capabilities:
- Universal JSON Support: JSON structured outputs are now available for all models across all tiers
- Complete Regex Support: Extending regex pattern support to all models (currently available for
sonarandsonar-reasoning) - Advanced Schema Validation: Enhanced validation options for more reliable structured data
- Output Templates: Pre-defined templates for common use cases
This expansion will make it easier to build applications that require consistent, structured data from our API responses.
We’re committed to making our documentation a truly exceptional resource:
- Improved Layout: Optimized structure for better self-serve workflows
- Consistent Design: Unified branding between our landing page and documentation
- Enhanced Content: Revised explanations for better developer understanding
- Vertical-Specific Guides: Specialized documentation for publishers, merchants, and other industry partners
- High-Fidelity Demos: More comprehensive examples beyond our basic cookbook demos
- Comprehensive Prompt Guide: In-depth resources to help you build effectively with our search + LLM API
- API Selection Guides: Clear guidance on which API is best suited for specific scenarios
These improvements will help you get up to speed faster and make the most of our API capabilities.
We’re scaling our infrastructure to support significantly higher request volumes:
- Working toward supporting use cases up to 100K RPM
- Designed for high-growth startups and enterprise applications
This enhancement will ensure our API can grow alongside your application’s user base and processing needs.
Improving our error framework:
- More descriptive error messages
- Clearer guidance on resolving common issues
This will reduce debugging time and help you understand and address issues more efficiently.
Broadening the types of content you can work with:
- URL Parsing: Extract and analyze content from web pages
These features will enable new use cases and richer interactions within your applications.
We’re working on exposing search results as a standalone API/product, separate from the end-to-end integration with the LLM.
This feature will allow developers to:
- Directly access search results without invoking the LLM.
- Build custom workflows and applications leveraging search capabilities independently.
This will provide greater flexibility for developers who only need search functionality.
We’re addressing the limitations of managing context in API calls by introducing new context management features.
Key improvements include:
- Efficient Context Storage: Avoid appending responses from previous API calls to new ones, reducing the risk of exceeding context windows.
- Session-Based Memory: Enable session-based memory to maintain context across multiple API calls without manual intervention.
These enhancements will make it easier to build applications that require persistent context without hitting technical limitations.
Timeline and Availability
This roadmap represents our current development priorities. Features will be released incrementally, with some becoming available in the coming months and others planned for later in the year.
We’ll announce new feature availability through our changelog and via email notifications to API users.