# Perplexity launches Orchestrator API for flexible model selection

> Source: <https://cryptobriefing.com/perplexity-launches-orchestrator-api/>
> Published: 2026-11-17 20:18:20+00:00

# Perplexity launches Orchestrator API for flexible model selection

Perplexity AI logo, trademark of Perplexity AI, Inc.; logo file public domain on Wikimedia Commons (recolored to brand…

The private preview routes requests across hosted open-weight models from Moonshot AI, Z.AI and DeepSeek under one key and one bill

[Perplexity](https://cryptobriefing.com/markets/perplexity/) has launched its Orchestrator API, a single gateway that picks models and providers for a given task and rolls the costs into one bill.

The service went live in private preview on November 9, 2026. It is aimed squarely at developers who are tired of juggling a different integration for every model they want to try.

## What the Orchestrator API actually does

The API gives developers unified access to a catalog of open-weight models that Perplexity hosts itself. Open-weight means the underlying model parameters are publicly released, so a company like Perplexity can run them on its own infrastructure.

Everything runs through a single base URL: **https://api.perplexity.ai/orchestrator/v1**. Developers authenticate with their existing Perplexity API key, so there is no new credential to manage.

The more interesting part is compatibility. The API accepts request formats from both [OpenAI](https://cryptobriefing.com/markets/openai/) and [Anthropic](https://cryptobriefing.com/markets/anthropic/), the two schemas most developers already have baked into their code.

Perplexity says developers can use any supported schema regardless of which lab originally built the model. That decoupling is the whole pitch: the format you write in no longer dictates the model you can call.

## The model lineup and the reliability layer

The initial catalog leans heavily on prominent open-weight releases. Listed models include:

### AI, tech, and the markets they move—in one daily briefing.

Daily. Free. Join 34,000+ readers across crypto, finance, and policy.

- **perplexity/kimi-k3** , from Moonshot AI
- **perplexity/glm-5.3** and**perplexity/glm-5.3-flash** , from Z.AI
- **perplexity/deepseek-v4-pro-0813** , from[DeepSeek](https://cryptobriefing.com/markets/deepseek/)

Developers can pull the full list programmatically through a **GET /orchestrator/v1/models** call. Pricing is published per million tokens for each model.

Each model ID comes with automatic request routing, health monitoring and failover across all deployments. If one deployment stumbles, traffic gets shifted elsewhere rather than returning an error to the user.

## How billing works

The billing model is pay-as-you-go, based on token usage at the published per-token rates. Tokens are the small chunks of text that models read and write, so the bill scales with how much work the model actually does.

Rejected requests, such as those that hit rate-limit errors, carry no charge.

Access is not open to everyone yet. Developers who want in during the private preview need to email [\[email protected\]](https://cryptobriefing.com/cdn-cgi/l/email-protection).

## Background: Perplexity’s busy 2026

The Orchestrator API is the latest in a string of developer-focused releases from Perplexity this year. Earlier in 2026, the company introduced its Agent API, and the new launch builds on that push into enterprise tooling.

The timing also lines up with other November 2026 initiatives, including Multiagent effort levels and Frontier Research projects.

The business numbers suggest the strategy is landing. Perplexity reported an annual recurring revenue run rate exceeding $1 billion as of mid-November 2026, a figure described as significantly higher than the prior year.

Company leadership has also floated the possibility of accelerating toward an IPO by 2027 as revenue climbs.

**Disclosure:** This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our [Editorial Policy](https://cryptobriefing.com/editorial-policy/).
