EmbeddingGemma 2
No published training cutoff
google/embeddinggemma-2
Price not published
Google’s Deep Research agent exposed to developers through the Interactions API.
Model iddeep-research-preview-04-2026
PricePrice not published
Checked9 October 2026
At least816events since its release in April 2026
38 historic, 196 major. 162 days of news.
Google doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.
2 ways to use Gemini Deep Research agent (API), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini API (Interactions API) | deep-research-preview-04-2026 |
https://generativelanguage.googleapis.com/v1beta/interactions |
ai.google.dev |
| Gemini API (Interactions API), Max tier | deep-research-max-preview-04-2026 |
https://generativelanguage.googleapis.com/v1beta/interactions |
ai.google.dev |
Price not published.
No price source linked. Checked 9 October 2026.
What its maker marketed at launch, and what people found later, each with its source.
Runs iterative searching and reading for several minutes and returns a synthesized report; only via the Interactions API with background=true (poll or stream), not generate_content. ‘Max’ trades speed for comprehensiveness.
Agent ids, not raw models; the underlying Gemini model and pricing are not stated on the docs page (checked 2026-10-09). The older deep-research-pro-preview-12-2025 was deprecated on 2026-10-08 and shuts down on 2026-10-23 (Gemini API changelog); migrate to deep-research-preview-04-2026 or deep-research-max-preview-04-2026.
See the docs page for request examples (background execution is required).
Sources: https://ai.google.dev/gemini-api/docs/deep-research , https://ai.google.dev/gemini-api/docs/changelog
Not yet checked against an official source: The ‘04-2026’ suffix suggests an April 2026 snapshot; exact release day not verified.
Paste this into a new chat. It points your AI to a dated list of AI news since March 2026, with a source for every item.
Files for every cutoff, with their sizes: Briefings.
For developers: an MCP server is planned. For AI agents