Perplexity launches Orchestrator API to route requests across model providers
Start here
Perplexity has launched the Perplexity Orchestrator API, a hosted inference gateway that puts frontier models from OpenAI, Anthropic, Google and xAI, along with open-weight models such as GLM, Kimi and DeepSeek, behind a single base URL. It accepts OpenAI Chat Completions, OpenAI Responses and Anthropic Messages request formats. Routing is in preview. Perplexity says there is no additional platform fee on top of credits, and requests that fail before producing output are not billed. Access is tiered by cumulative credit purchases: Tier 0 covers Google, xAI and open-weight models.
Generated from reports · updated 29 min ago
Report timeline
Follow the reports to see the event from different sides.
- MarkTechPostPerplexity launches Orchestrator API for failover and model routing
Perplexity launched the Perplexity Orchestrator API, a hosted inference gateway that serves frontier models from OpenAI, Anthropic, Google and xAI plus open-weight models such as GLM, Kimi and DeepSeek behind one base URL, accepting OpenAI Chat Completions, OpenAI Responses and Anthropic Messages requests.
Heat for this event
Not enough continuous observations yet to draw a trend.