InfraPerplexityConfirmed
Story 4 of 18 in the Tuesday 17 November editionPerplexity launches Orchestrator API to route across 45+ AI models
Live on 17 November 2026 with OpenAI Responses, Chat Completions and Anthropic Messages compatibility, consolidated billing and perplexity/auto failover.

Perplexity launched the Perplexity Orchestrator API on 17 November 2026, giving developers unified access to more than 45 open-weight and proprietary models from OpenAI, Anthropic, Google, xAI and open-source labs through one API key and consolidated billing. Following its 16 November Perplexity Monitor API launch, the gateway accepts OpenAI Responses, OpenAI Streaming Chat Completions and Anthropic Messages schemas and can attach Perplexity web search and inline citations in one call.
Task-aware perplexity/auto model selection and provider failover
Developers can pin an explicit model ID such as claude-fable-5-2 or target the perplexity/auto router, which inspects each request to balance task capability against cost and latency before selecting an underlying deployment based on live provider availability and capacity. If a primary deployment fails or throttles, Orchestrator automatically retries across healthy endpoints without client-side routing code.
Perplexity published per-model context windows, output token limits, prompt-caching rules, safety identifiers, Analytics API telemetry, AWS Marketplace billing options and Sonar migration guides across docs.perplexity.ai.
Technical details
- Supported model catalogue
- 45+ proprietary and open-weight models across OpenAI, Anthropic, Google, xAI and open-source providers
- Wire-protocol compatibility
- OpenAI Responses, OpenAI Streaming Chat Completions and Anthropic Messages formats
- Routing identifier
- perplexity/auto dynamic model and provider selection with automatic deployment failover
- Enterprise administration
- Consolidated billing, AWS Marketplace support, safety identifiers, prompt caching and Analytics API
Release details & context
Two-stage model and deployment selection plus sandbox web-search rates
Perplexity’s routing architecture separates model choice from infrastructure placement: when a client passes perplexity/auto, the first stage matches prompt complexity to a candidate model, and the second stage scores active inference providers by capacity, error rates and latency before dispatching the stream, complementing Perplexity’s Decider v1.3 routing models.
Existing Perplexity API keys work across Orchestrator, Search, Agent, Embeddings, Decisions and Monitor endpoints without separate onboarding, and optional SDK web_search calls executed from agent sandboxes bill at $0.0025 per search request.
Common questions
Which SDK request formats does the Perplexity Orchestrator API accept?
Orchestrator accepts OpenAI Responses, OpenAI Streaming Chat Completions and Anthropic Messages request formats under a single Perplexity API key.
Sources
- PrimaryPerplexity Orchestrator API Quickstartdocs.perplexity.ai
- OfficialOrchestrator Models & Pricing - Perplexity Docsdocs.perplexity.ai
- OfficialRouting & Reliability - Perplexity Docsdocs.perplexity.ai
- OfficialPerplexity API Platform Pricingdocs.perplexity.ai
- On XPerplexity (@perplexity_ai) Orchestrator API launch post on Xx.com
- On XAravind Srinivas (@AravSrinivas) on 45+ Orchestrator models on Xx.com
Perplexity release timeline (13 launches tracked)
- Perplexity brings Teammates to the Perplexity Mac app for Max users
Perplexity rolls out Teammates in the Perplexity Mac app for Max subscribers to run solo or multi-agent QA, support and research tasks.
- Perplexity launches Monitor API for scheduled web and page webhooks
Perplexity launches the Monitor API to watch web topics or up to 10 URLs on cron schedules and send Decider-filtered webhooks at $1 per 1k runs.
- Perplexity launches Frontier Research lab backed by 10,000+ GPUs
Perplexity forms Perplexity Frontier Research with 10,000+ GPUs to build autonomous research systems and publish open-source models and data.
- Perplexity launches Context API for agent URL extraction at $1 per 1k
Perplexity ships its Context API at $1 per 1,000 successful URLs, hitting 92.3% usable extraction and 87.9% fact recall across 715 sites.

