Sulat.com / Writing on AIThursday, November 19, 2026
Agents/19 November 2026

Perplexity’s Orchestrator API puts frontier and open-weight models behind one key

Perplexity's new Orchestrator API gives one endpoint to Claude, Gemini, Grok and open-weight models, with failover to another provider when a call fails. It bills per token with no platform fee.

The Perplexity logo on a brass switchboard hub, with glowing teal tracks fanning out to dozens of model stations and one track rerouting around a broken station

At a glance

  • Perplexity's Orchestrator API gives one endpoint to models from Anthropic, Google, xAI, OpenAI and open-weight labs, and works with the OpenAI and Anthropic SDKs by changing the key and base URL.
  • If a call fails, times out or hits a rate limit, it retries the same model on another provider, such as AWS Bedrock instead of Anthropic, without changing the per-token price.
  • Routes, in preview, let you describe which requests each model should handle in plain language, with a default model used when nothing matches.
  • Billing is per token at each model's published rate with no platform fee, and Claude Opus and Fable models need usage Tier 2.

Perplexity has launched the Orchestrator API, one endpoint that reaches models from Anthropic, Google, xAI, OpenAI and open-weight labs such as GLM, Kimi and DeepSeek. It chooses the provider for each call based on availability, capacity and latency, and bills everything against a single pool of credits with no platform fee added. The headline claim is reliability: across a month of Perplexity’s own production traffic, Claude requests succeeded more often through the Orchestrator than on any one provider it measured.

Perplexity announced the API on X on 17 November, alongside two blog posts. Co-founder and CTO Denis Yarats added his own thread. His argument is that general-purpose model routing breaks the KV cache and is usually tuned to a handful of benchmarks, so Perplexity leaves the choice of model per task to you. The API follows the Context API and Monitor API, which Perplexity launched earlier this month.

One endpoint, many providers

Behind the API sits the model layer Perplexity already runs for its own products. It handles hundreds of millions of requests across more than 85 models and over a dozen providers, with open-weight models served by Perplexity or its inference partners. The endpoint accepts three request formats: OpenAI Chat Completions, OpenAI Responses and Anthropic Messages. To switch an existing app over, you swap the API key and the base URL. The docs give that URL as api.perplexity.ai/orchestrator/v1, and model IDs carry a provider prefix, for example anthropic/claude-fable-5-2 or perplexity/glm-5.3. Calling the models endpoint returns the list your tier can use. There’s no server-side state between requests.

You pay per token at each model’s published rate, and there’s no per-request fee. Cache reads get a discount, while reasoning tokens count as output. The API Console breaks spend down by model, project, API key and date. Admins can restrict models, limit users and set spend caps.

Failover and routing

Failover keeps the same model and changes where it runs. If a Claude call errors, hits a rate limit or times out on Anthropic, the Orchestrator retries it on another deployment, such as AWS Bedrock. Every attempt has its own cap on time to first token and total duration, and the per-token rate stays put. Perplexity tracked success rates from 4 October to 2 November and says Claude through the Orchestrator beat each provider on its own, with less swing from day to day.

Diagram: an app calls Orchestrator, which retries a Claude Opus 5.5 request that failed on Anthropic and succeeds on AWS Bedrock
A failed call is retried on another deployment of the same model.

Providers also differ on speed. For Claude Opus 5.5, Anthropic had the faster median output speed on 15 of the 30 days Perplexity looked at, and AWS Bedrock led on the other 15. Perplexity says it’s building routing that accounts for speed.

Two features are still in preview. The first is routes. You write a plain-language description of the requests each model should take and pick a default for everything else. Perplexity’s support example defaults to GLM-5.3 Flash, sends billing disputes to Claude Opus 5.5 and sends technical problems to GPT-6.1 Sol. A small decision model reads the conversation and the route descriptions, never the model names. If nothing matches, or the decision model fails or times out, the default answers. Response headers say whether the request was routed and which route won. The second preview feature, Auto effort, changes the reasoning effort on a supported model’s next turn according to a policy you set.

Diagram: a decision model reads two support messages and sends billing_dispute to Claude Opus 5.5, technical_issue to GPT-6.1 Sol, and anything else to GLM-5.3 Flash
Perplexity’s support example, with the route names the decision model matches on.

Prompt caches don’t carry across models. Perplexity’s advice is to send a stable prompt_cache_key so a conversation stays on one deployment, though that’s best effort and a failover can still move it. With no routing object at all, simple requests go to GPT-6 Luna and everything else goes to GPT-6.1 Sol.

One test covers refusals. Perplexity cites Anthropic’s own documentation that Claude Fable 5.2’s safeguards can block some harmless cybersecurity and biology work. On a 63-task subset of Terminal-Bench 4.1, Claude Code with Fable alone solved 38 tasks. When routes passed refused requests to another vendor’s model, it solved 41, and the estimated cost per task went up.

What it costs

Which models you can call depends on your usage tier. Google, xAI and open-weight models start at Tier 0, OpenAI and Anthropic models at Tier 1, and Claude Opus 5, Opus 5.5 and the Fable models at Tier 2. A call above your tier returns HTTP 402. The Fable models can’t be used with zero data retention.

Staircase diagram: Tier 0 unlocks Google, xAI and open-weight models, Tier 1 adds OpenAI and Claude Sonnet and Haiku, Tier 2 adds Claude Opus and the Fable models
Each tier adds models; a call above your tier fails with HTTP 402.
ModelInput per 1M tokensOutput per 1M tokensTier
Claude Fable 5.2US$8.00US$40.002
Claude Opus 5.5US$4.00US$20.002
Claude Sonnet 5.5US$2.00US$10.001
Claude Haiku 5.5US$0.10US$0.501
Gemini 3.8 FlashUS$0.75US$3.750
Grok 4.7US$2.00US$6.000
GLM-5.3US$1.40US$4.400
GLM-5.3 FlashUS$0.15US$0.500
DeepSeek V4 ProUS$1.32US$3.960
Kimi K3US$3.00US$15.000
Source: Perplexity’s Orchestrator model catalogue. Haiku’s rate holds up to 100,000 input tokens, and Gemini 3.8 Flash’s holds through 31 December 2026.

Cache writes cost extra on some models: 1.25 times the input rate for Anthropic and several OpenAI models, and twice the input rate for Anthropic’s one-hour cache. Credits can be bought through AWS Marketplace. Teams with large or committed workloads can email [email protected] about volume pricing and capacity, and the same address takes requests for models missing from the catalogue.


Discover more from Sulat AI & Tech News

Subscribe to get the latest posts sent to your email.