Releasesby GlyphExa Deep Revamp
Exa Deep Revamp Exa Deep is faster, cheaper, and now supports structured outputs with field-level grounding. New deep-reasoning type for higher-effort tasks (12-50s); deep runs in 4-12s. 20% lower price for regular deep search.
Also shipped Jun 15, 2026Exa in June 2026 →
You can publish a Cloud SQL for MySQL conversational analytics agent in Gemini Enterprise
You can publish a Cloud SQL for MySQL conversational analytics agent in Gemini Enterprise . This feature is in Preview . Cloud SQL for PostgreSQL
You can publish a Cloud SQL for PostgreSQL conversational analytics agent in Gemini Enterprise
You can publish a Cloud SQL for PostgreSQL conversational analytics agent in Gemini Enterprise . This feature is in Preview .
The following Anthropic models are deprecated from DigitalOcean Inference as of 15 June 2026: Claude Opus 4...
The following Anthropic models are deprecated from DigitalOcean Inference as of 15 June 2026: Claude Opus 4 Claude Sonnet 4 Migrate to Claude Opus 4.8 (anthropic-claude-opus-4.8) and Claude Sonnet 4.6 (anthropic-claude-4.6-sonnet), …
Snapshots is now in Open Beta
Get screenshot diffing in CI to catch unintended visual changes. Works for any platform with a frontend.
Dashboard Search for APIs Now in Beta
__Dashboard Search for APIs is now available in Public Beta!__ Find your API faster without scrolling through paginated lists. Dashboard users can now __search APIs in real time by ID, identifier or name.__ Rolling out progressively to Public Cloud tenants starting this week, with broader availability in the coming weeks.
Week 25
Address data collection The Collect Data task has a new address type. Add it to an agent and it walks the caller through providing a complete mailing address (street, city, postcode, country) in one structured step, validating the input and writing the parsed fields back onto the contact.
More from ExaEvery Exa release →
API Deprecation Notice
API Deprecation Notice We retired a few legacy items from the Exa API: /research endpoint : replaced by /search with type: "deep-reasoning" . resolvedSearchType and highlightScores (response fields) : returned null from April 15, removed May 1. startCrawlDate / endCrawlDate (deprecated request parameters) : silently ignored from April 15.
Introducing Exa Monitors
Introducing Exa Monitors Monitors run Exa searches on a schedule and deliver results to your webhook, deduplicated against previous runs so you only get new content. Track topics over time : competitor news, funding rounds, regulatory changes, research papers. Structured results : return plain text or typed JSON via outputSchema .
Exa Pricing Update
Exa Pricing Update We simplified and lowered pricing. Contents for the first 10 search results are now included for free, and the new pricing applies automatically with no action needed. Search with contents : $7 per 1k requests (10 results, text + highlights included); $1 per 1k additional results. Summaries : $1 per 1k, on both search and contents.
Introducing Exa Instant Search
Introducing Exa Instant Search Exa Instant is our fastest search type, combining improved neural search quality with sub-150ms latency. Enable it with type="instant" . Built for real-time : chat apps, voice AI, coding agents, autocomplete, and live suggestions. State-of-the-art quality at the lowest latency we offer.
Highlights, content freshness, and MCP updates
Highlights, content freshness, and MCP updates Three improvements to content extraction and access: maxCharacters for highlights : now the preferred way to control highlight length. numSentences and highlightsPerUrl are deprecated.
Introducing Exa Company Search
Introducing Exa Company Search Company search now uses a fine-tuned retrieval model and entity-matching pipeline. Use type="auto" , category="company" . Accurate across attributes : industry, geography, funding stage, and employee count. Structured entity data : results return typed company info (workforce, HQ, financials, web traffic).
Introducing Exa People Search
Introducing Exa People Search People search now spans 1B+ public profiles via a hybrid retrieval system. The linkedin category is replaced by the new people category. Broader coverage : profiles across the whole web, not just LinkedIn. Better accuracy : fine-tuned embeddings for role, skill, and company queries.
JS SDK: highlights restored
JS SDK: highlights restored Highlights are back in the JavaScript SDK as of exa-js v2.0.11, returning key sentences with relevance scores. Pass highlights: true or highlights: { maxCharacters, query } in search and contents calls. Read the JavaScript SDK docs →