Perplexity

AI search and answer platform for developers.

Perplexity API Changelog Monitoring

Perplexity is an AI search and answer platform for developers, offering APIs for search, research, and cited responses. This Perplexity API Changelog Monitoring page helps teams track product changes quickly so they can keep integrations, internal tools, and customer-facing features aligned with the latest platform behavior.

Strong Perplexity API Changelog Monitoring helps teams catch model updates, API changes, deprecations, pricing adjustments, and new developer features before they create downstream issues. It also supports better release planning by giving engineering and product teams a shared view of what changed and what may require action.

The benefit of Perplexity API Changelog Monitoring is simple: your team gets a repeatable way to review updates, evaluate integration risk, and respond before upstream platform changes affect production systems. Perplexity API changelog and developer updates

Perplexity API down?

Perplexity API down? For live availability checks, refer to Perplexity's official status or support channels. This page is focused on Perplexity API Changelog Monitoring, helping you follow releases, feature announcements, and breaking changes that may affect your integration over time.

Recent changes

Showing the last 10 changes from this feed.

10-15-2026

October 2026

NVIDIA Nemotron 3.5 Super The Agent API now supports perplexity/nemotron-3.5-super-120b-a12b at $0.20 per million input tokens, $0.04 per million cached input tokens, and $0.50 per million output tokens. It has a 1,048,576-token context window, returns up to 131,072 output tokens, and accepts text input only. It replaces perplexity/nemotron-3-ultra-550b-a55b, which is no longer listed in the Agent API or Orchestrator API model docs. See the Agent API Models reference.

Source

10-09-2026

October 2026

Decisions API: pplx-decider-v1.1-27b replaces v1 pplx-decider-v1.1-27b replaces pplx-decider-v1-27b as the Decisions API model. Input now costs $0.02 per million tokens, down from $0.04. Use pplx-decider-v1.1-27b in new requests. Requests that still name pplx-decider-v1-27b continue to work and bill at the same $0.02 rate. See Pricing and the Decisions API quickstart.

Source

10-07-2026

October 2026

Claude Haiku 5.5 The Agent API now supports anthropic/claude-haiku-5-5. Requests with more than 100k input tokens use higher rates. See the Agent API Models reference.

Source

10-05-2026

October 2026

Low, medium, and high presets use Fast Search The Agent API low, medium, and high presets now use Fast Search (search_type: "fast") for web_search, matching the fast preset. web_search calls made under these presets drop from $2.50 to $1.00 per 1,000 invocations, and search is about 800 ms faster. The xhigh preset is unchanged and continues to use standard web search. Models, prompts, tool budgets, and step limits are unchanged. To keep standard web search under any preset, set search_type: "web" on the web_search tool. See Agent API Web Search.

Source

09-29-2026

September 2026

Claude Sonnet 5.5 The Agent API now supports anthropic/claude-sonnet-5-5. See the Agent API Models reference.

Source

09-28-2026

September 2026

xhigh preset uses Claude Opus 5.5 The Agent API xhigh preset now uses Claude Opus 5.5: Preset Previous model New model xhigh openai/gpt-5.6-sol anthropic/claude-opus-5-5 Prompts, reasoning effort, tools, token budgets, and step limits are unchanged.

Source

09-25-2026

September 2026

Fast preset uses Fast Search The Agent API fast preset now uses Fast Search (search_type: "fast"). web_search drops from $2.50 to $1.00 per 1,000 invocations, and search is about 800 ms faster. See Agent API Web Search.

Source

09-24-2026

September 2026

Fast Search Set search_type: "fast" on the Search API or the Agent API web_search tool to use a lower-latency search path. Fast Search costs $1.00 per 1,000 Search API requests or web_search invocations, with model tokens billed separately for Agent API. Set search_type: "web" for standard web search. See Search API Fast Search or Agent API Web Search.

Source

09-24-2026

August 2026

Fast preset updated The Agent API fast preset now uses openai/gpt-6-luna with reasoning effort set to none and priority processing. Dynamic fast preset requests pick up the change automatically. If you use a frozen configuration, update the model and reasoning effort and set service_tier to priority. Priority processing uses 2× the model's standard token prices.

Source

09-22-2026

September 2026

GPT-6 Sol The Agent API now supports openai/gpt-6-sol. See the Agent API Models reference. GPT-6 Luna The Agent API now supports openai/gpt-6-luna. See the Agent API Models reference. Claude Opus 5.5 The Agent API now supports anthropic/claude-opus-5-5. See the Agent API Models reference. Grok 4.7 The Agent API now supports xai/grok-4.7. See the Agent API Models reference.

Source