Superpower Daily
OpenAI’s 10-Day WebMCP Challenge Pushes Websites to Expose Tool...Model-Serving Platforms Reach 6.1% of AI-Spending Businesses, W...Gemini Omni 1.1 Flash Adds 40-Second Scene Extensions and 4K Fi...Harvard Uses 7 AI Faculty Avatars in a $699 Founder Bootcamp, W...Databricks Says 300M Chart-JSON Pipeline Tops Four Multimodal B...Nvidia’s $63.1 Billion Receivables Add a Cash-Flow Caveat to It...OpenAI’s 10-Day WebMCP Challenge Pushes Websites to Expose Tool...Model-Serving Platforms Reach 6.1% of AI-Spending Businesses, W...Gemini Omni 1.1 Flash Adds 40-Second Scene Extensions and 4K Fi...Harvard Uses 7 AI Faculty Avatars in a $699 Founder Bootcamp, W...Databricks Says 300M Chart-JSON Pipeline Tops Four Multimodal B...Nvidia’s $63.1 Billion Receivables Add a Cash-Flow Caveat to It...
Toolspublished

Perplexity Puts Open-Weight Models Behind One API, With OpenAI and Anthropic Formats

The compatibility layer lets developers retain familiar client interfaces while Perplexity takes on deployment routing; access is still limited to a private preview.

By 2 min read
Perplexity Puts Open-Weight Models Behind One API, With OpenAI and Anthropic Formats
Sign in to save and react

Listen to this story

The audio brief

About 1:32
0:001:32
Read transcript
Perplexity is privately previewing Router API, a single access layer for the open-weight models it hosts. Developers can use familiar OpenAI or Anthropic request formats, while Perplexity handles the less visible infrastructure: sending each request to a healthy deployment and managing failover. The important distinction is that Router does not choose the model for the task. Developers still select a catalog model, including Perplexity IDs for DeepSeek V4 Flash, GLM-5.2, and Kimi K3. Perplexity then manages availability behind that choice. Billing follows the selected model’s published input, output, and cache-read rates, even if another deployment serves the request. For teams with existing integrations, the appeal is compatibility. OpenAI users primarily change the base URL and API key. Anthropic SDK users point their client to a different Router base URL. Both use Perplexity credentials, rather than separate accounts and software development kits for each provider. There are tradeoffs. OpenAI Responses requests are stateless, so applications must send the full conversation every time. And Router is for direct model access with a developer’s own prompts and tools—not web-grounded answers with citations. Perplexity directs those use cases to its separate Agent API. The immediate constraint is access: Router API remains a private preview, available only by requesting entry by email. The thing to watch is whether this compatibility-and-routing approach moves from gated test to broadly available infrastructure.

Story brief

3 key points

Perplexity is privately previewing Router API, a compatibility layer that lets developers access its hosted open-weight model catalog through OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages formats. Developers still choose the model; Perplexity handles deployment health and failover, while billing follows the selected model’s published rate. The service could simplify multi-model infrastructure, but...

  1. 01

    The catalog lists Perplexity IDs for DeepSeek V4 Flash, GLM-5.2, and Kimi K3.

  2. 02

    Routing manages availability and failover; it does not automatically select a model for a task.

  3. 03

    Customers pay the selected model’s published input, output, and cache-read rates.

Perplexity has put its Router API into private preview, offering one API key for open-weight models it hosts. Developers choose a catalog model through familiar OpenAI or Anthropic request formats, while Perplexity says it sends each request to a healthy deployment.

One catalog, three request languages

The Router accepts OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages formats. Perplexity says any catalog model can be called through any of those schemas, regardless of its original provider. The service is therefore a compatibility layer around Perplexity-hosted models, rather than a new request protocol for developers to adopt.

For an existing OpenAI integration, Perplexity says the required changes are the base URL and API key. Anthropic SDK users point to a different Router base URL because that SDK adds its own versioned Messages path. Both paths use Perplexity credentials, removing the need for separate provider accounts and SDKs.

Model selection is not automatic

The routing is about availability, not task-level model choice. A developer still names a model from the catalog; Perplexity then routes that request to a healthy deployment. The documented catalog includes Perplexity IDs for DeepSeek V4 Flash, GLM-5.2, and Kimi K3.

That split also applies to billing. Perplexity says customers pay the selected model’s published rate even if another deployment serves the request. Its catalog endpoint lists current model IDs and base input, output, and cache-read prices in U.S. dollars per one million tokens.

Familiar endpoints, some Router-specific details

The documented chat-completions endpoint uses bearer-token authorization and the OpenAI conversation schema. It supports function tools with a name, parameters, and strictness setting. Streaming uses server-sent events, and an include_usage option returns token usage in the final streamed chunk.

Applications using the OpenAI Responses format face one important difference: Perplexity documents that endpoint as stateless, requiring the full conversation in every request. Router is meant for direct model access with a developer’s own prompts and tools; Perplexity directs users wanting web-grounded answers with built-in citations to its separate Agent API.

Access remains the immediate limit

Router API is not yet broadly available. Perplexity labels it a private preview and asks developers to request access by email, making the current release a gated test of its compatibility and managed-routing approach.

Sources

  1. docs.perplexity.aiPerplexity Router API - Perplexity
  2. docs.perplexity.aiPerplexity Router API - Perplexity
  3. docs.perplexity.aiCreate Chat Completion - Perplexity

Related coverage

Continue reading