- Google introduces two updates to Gemini API enhancing Deep Research capabilities and quality
- Users can choose Deep Research for speed or Deep Research Max for highest quality context synthesis
- Deep Research offers reduced latency, lower cost, and suits interactive, low-latency research needs
Google on Tuesday announced the introduction of two new updates to Gemini API that seek to offer distinguished but high-quality results to users.
"We are launching two powerful updates to Deep Research in the Gemini API, now with better quality, MCP support, and native chart/infographics generation," said Sundar Pichai, the chief executive officer of Google-parent Alphabet Inc, in a post on social media platform X.
The new update allows users to select either "Deep Research" or "Deep Research Max" for their queries, depending on the results they desire.
"Use Deep Research when you want speed and efficiency, and use Max when you want the highest quality context gathering & synthesis using extended test-time compute — achieving 93.3% on DeepSearchQA and 54.6% on HLE," Pichai added.
We are launching two powerful updates to Deep Research in the Gemini API, now with better quality, MCP support, and native chart/infographics generation.
— Sundar Pichai (@sundarpichai) April 21, 2026
Use Deep Research when you want speed and efficiency, and use Max when you want the highest quality context gathering &… pic.twitter.com/rTp7R6w3IT
ALSO READ: Anthropic's Claude Mythos Is Striking Fear Into The Heart Of Banks — Here's Why
Deep Research
This new agent replaces "our preview release from December" and delivers significantly reduced latency and cost at higher quality levels, Google said in a blogpost. It is the ideal agent for research experiences integrated directly into interactive user surfaces where lower latency is desired, it added.
Deep Research Max
This is designed for "maximum comprehensiveness and highest-quality synthesis", it said, adding that Max leverages extended test-time compute to iteratively reason, search and refine the final report. It is the "perfect engine" for asynchronous, background workflows such as a nightly cron job triggering the generation of exhaustive due diligence reports for an analyst team by morning, Google noted.
MCP Support
Deep Research allows users to seamlessly connect their custom data and specialised professional data streams (such as financial or market data providers) securely via MCP, or Model Context Protocol. "Deep Research supports arbitrary tool definitions which transforms it from a web searcher into an autonomous agent capable of navigating any specialized data repositories," the blogpost stated.
Native Charts
"A first for Deep Research in the Gemini API, our agent no longer just creates text; it natively generates high-quality charts and infographics in-line with HTML or Nano Banana, dynamically visualising complex data sets to enrich analytical reports," Google further stated.
ALSO READ: Anthropic Launches Claude Opus 4.7 With Improved Benchmark Performance
Essential Business Intelligence, Continuous LIVE TV, Sharp Market Insights, Practical Personal Finance Advice and Latest Stories — On NDTV Profit.
