Releasesby GlyphOctober 2026
Tool approvals for MCP and connector calls Set require_approval on an mcp or connector tool to review calls before they run. A call that needs approval returns an mcp_approval_request item and does not run. To approve or deny it, send an mcp_approval_response with previous_response_id .
Also shipped Oct 19, 2026Perplexity in October 2026 →
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4...
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4 Flash (0731) will be removed from the shared Serverless Training pool. This change applies only to Serverless Training. If you train DeepSeek V4 Flash (0731) on Serverless Training, migrate to DeepSeek V4.1 Flash 1017 before November 2, 2026.
Cloud Workload Security is now available in Beta
Cloud Workload Security (CWS) is now available in Beta. Apply policy controls to cloud API requests before they reach your cloud provider. Define policies with request filters and Rego checks. For example, block requests that would make an R2 bucket public. Use workloads and policy sets to target your cloud environments.
Copilot model policy API for enterprise, orgs, and teams
You can now use the REST API to retrieve and update Copilot model policies for enterprises, enterprise teams, enterprise apps, and organizations. What’s new GET and PATCH endpoints are now generally available for model policies at four levels: Enterprise: /enterprises/{enterprise}/copilot/model-policies Enterprise teams...
GitHub Copilot models deprecated on October 19, 2026
As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). These deprecations were announced on September 18, 2026 .
Postgres wait events, now in Query Insights
Query Insights for ClickHouse Managed Postgres now includes wait event breakdowns, blocked-session charts, and lock-wait charts. These metrics are also available in Prometheus.
Send OpenTelemetry traces to Agent Observability, no SDK required
You can now send OpenTelemetry traces straight to Agent Observability, without the SDK. If your agents already emit OpenTelemetry generative AI spans, from your framework, an instrumentation library, or spans you write yourself, keep your existing route through Grafana Alloy or an OpenTelemetry Collector and opt in your AI spans with a single attribute.
More from Perplexity APIEvery Perplexity API release →
October 2026
Older models removed from the model docs; GPT-6 Astra and DeepSeek V4 Pro added The following models are no longer listed in the Agent API model docs, pricing calculator, or examples: Anthropic: anthropic/claude-opus-4-8 , anthropic/claude-opus-4-7 , anthropic/claude-opus-4-6 , anthropic/claude-opus-4-5 , anthropic/claude-sonnet-4-6 ...
October 2026
Agent API: preset renamed to effort This is a naming change only. Effort levels keep the same models, prompts, tools, limits, and pricing. Version pinning and frozen configurations continue to work as before. preset is still accepted as a deprecated alias, and responses return both fields. See Effort .
October 2026
Decisions API: pplx-decider-v1.2 and pplx-decider-flash-v1.2 pplx-decider-v1.2 replaces pplx-decider-v1.1-27b as the 27B decision model, at $0.02 per million input tokens. pplx-decider-flash-v1.2 is a new 4B decision model at $0.01 per million input tokens. Both accept text and images and use the same request limits. Output tokens stay free.
October 2026
Gemini 4 Argon The Agent API now supports google/gemini-4-argon . Introductory pricing through November 30, 2026 is $2.00 per million input tokens, $0.10 per million cached input tokens, and $10.00 per million output tokens, including reasoning tokens. See the Agent API Models reference .
October 2026
Agent API: effort level updates and the ultra-preview effort level These effort level changes were not listed in earlier changelog entries. Each line names the current version. Earlier versions stay available as pinned versions . fast ( fast@2026-10-16.0 ): falls back to openai/gpt-5.6-luna when openai/gpt-6-luna is unavailable.
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 .
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 .
August 2026
GLM 5.3 The Agent API and Router API now support perplexity/glm-5.3 at $1.40 per million uncached-input tokens, $0.26 per million cached-input tokens, and $4.40 per million output tokens. See the Agent API Models reference or the Router model catalog .