product update

Perplexity launches Orchestrator API with same-model provider failover and consolidated billing

TL;DR

Perplexity launched Orchestrator on November 17, 2026, an API for accessing proprietary and open-weight models hosted on its inference infrastructure. It offers consolidated billing, same-model provider failover and an optional automatic model-routing feature in preview.

1 min read
0

Perplexity launched Orchestrator on November 17, 2026, an API for accessing proprietary models and open-weight models hosted on the company's inference infrastructure, according to a report from Unite.AI.

What Orchestrator provides

The API includes three listed features:

  • Consolidated billing across the models available through the service.
  • Same-model provider failover, which keeps requests for a selected model flowing across providers.
  • Automatic model routing, an optional feature currently in preview.

How routing works

Perplexity's routing documentation separates two decisions. The first is model selection. Once a model is selected, provider routing distributes traffic among deployments of that model using observed error rates, capacity and latency.

Pricing, context window sizes, supported model lists and benchmark figures were not part of the report.

What this means

Orchestrator separates choosing a model from choosing where it runs. Provider routing based on observed error rates, capacity and latency operates after the model is chosen, so failover applies to deployments of the same model. The automatic model-routing feature is still in preview, so the model-selection layer is the part of the product that is not yet generally available.

Source: unite.ai ↗

Related Articles

product update

Perplexity Brain Can Now Create and Update Agent Skills; 80,000+ Personal Skills Written for 20,000+ Users

Perplexity said on November 18, 2026, that Brain, the personalization system for its Computer agent, can now create and update reusable agent skills. According to the company, Brain wrote more than 80,000 personal skills for over 20,000 users between August 1, 2026, and November 14, 2026.

product update

GitHub Copilot team customizations now generally available for organization teams

GitHub announced that team customizations for GitHub Copilot are generally available for organization teams. The feature lets teams share the Copilot plugins they rely on without asking every member to repeat the same setup.

product update

Google adds "temporary threads" to AI Mode in Search, detaching chats from your account

Google is adding "temporary threads" to AI Mode in Search, a chat option that detaches the session from the user's account. The conversations won't resurface in search history or recommendations. The feature is rolling out globally on desktop and mobile across all supported languages.

product update

Databricks Genie in Microsoft Teams is now generally available, with Copilot Cowork and Excel integrations

Databricks says its Genie app for Microsoft Teams is now generally available, and Genie Ontology is generally available too. Genie also connects to Microsoft Copilot Cowork, Copilot Chat, Excel and Copilot Studio, with Unity Catalog enforcing each user's data permissions.

Comments

Loading...