Releasesby GlyphJuly 2026
GPT-5.6 price cuts and Sol Fast mode GPT-5.6 Luna now costs $0.20 per million input tokens and $1.20 per million output tokens. GPT-5.6 Terra now costs $2 per million input tokens and $12 per million output tokens. GPT-5.6 Sol now supports Fast mode at 2× standard token pricing; send service_tier: "priority" to use it.
Also shipped Aug 10, 2026Perplexity in August 2026 →
BigQuery supports gemini-3.1-flash-lite and gemini-3.5-flash GA models
Both models work in all BigQuery generative AI functions and are available on the us, eu and global multi-regional endpoints.
AI_MULTI_EMBED support for large video files in semantic video search (General availability)
Snowflake Cortex AI_MULTI_EMBED is now generally available for semantic video search with support for large video files up to 6 GB using the TwelveLabs Marengo Embed 3.0 model, enabling organizations to index and search production-grade video content directly in Snowflake.
Amazon S3 Tables Iceberg REST catalog integration (General availability)
Snowflake can now connect directly to the Amazon S3 Tables Iceberg REST endpoint, so you don’t need to create an AWS Glue integration. This capability is now generally available.
Request Access in Workspaces (Preview)
With this preview release, you can resolve access-related SQL errors in Workspaces by submitting access requests directly from Snowsight. When a query fails because of missing privileges and the user can’t self-resolve the issue by switching roles, the user can submit a request with a reason.
READ METADATA privilege is GA
The READ METADATA privilege is now generally available in Unity Catalog. READ METADATA provides read-only visibility into the same metadata available to the object's owner or a user with MANAGE , including security-sensitive information that BROWSE doesn't expose, such as privilege grants, row filters and column masks, and ABAC policies.
Notion connector (Beta)
The managed Notion connector in Lakeflow Connect is now available in Beta. The connector ingests pages, data sources, databases, blocks, comments, and users from Notion into Databricks. See Notion connector .
More from Perplexity APIEvery Perplexity API release →
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 .
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 .
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 .
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
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
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
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 .
October 2026
The Agent API has renamed the preset parameter to effort. This is a naming change only, and existing configurations remain functional.