GenAI PMGemini API
Google’s API for accessing Gemini models. The newsletter says Gemini 3.7 Flash is available in it and being rolled out to paid users.
Key Highlights
- Gemini API is Google’s platform for accessing Gemini models, agents, multimodal features, and first-party tools like Search and Maps.
- In 2026, the platform expanded quickly with managed agents, background tasks, scheduling, function calling, and cost controls.
- Support for combining Google Search and Google Maps made Gemini API more relevant for grounded and location-aware applications.
- Gemini 3.7 Flash was reported as available in the Gemini API and rolling out to paid users in August 2026.
- For AI PMs, Gemini API is especially useful for testing autonomous workflows, multimodal product ideas, and production-ready agent patterns.
At a glance
- Website
- https://ai.google.dev
- Category
- API
Gemini API
Overview
Gemini API is Google’s developer API for accessing the Gemini family of models and related agent, multimodal, and tool-use capabilities. Based on newsletter coverage, it has evolved beyond basic text generation into a broader platform for building AI products with model access, hosted agents, search and maps tool integrations, robotics endpoints, image/video workflows, and operational controls for production use. The newsletter specifically notes that Gemini 3.7 Flash became available in the Gemini API and was rolling out to paid users as of August 2026.For AI Product Managers, Gemini API matters because it represents a fast-moving Google ecosystem surface where new model variants, agent frameworks, and first-party tools can quickly change product scope, cost structure, and time-to-market. Its connection to Google AI Studio and Google services such as Search and Maps makes it especially relevant for PMs evaluating multimodal assistants, location-aware experiences, autonomous workflows, and enterprise-facing agent products.
Key Developments
- 2026-05-20: Google AI Studio and the Gemini API received major updates including Gemini 3.5 Flash, managed agents with the antigravity harness, native Android app creation in AI Studio, workspace integrations, and one-click antigravity export.
- 2026-05-22: A GitHub Issue Triage Agent was demonstrated using a single curl call to the Gemini API, highlighting low-friction agent prototyping.
- 2026-06-02: Managed Agents launched in the Gemini API, enabling autonomous agents that can reason, write and run code, and manage files in a hosted Linux sandbox via one API call.
- 2026-07-01: Gemini Omni Flash rolled out via the Gemini API and Google AI Studio to support high-quality video generation and editing; the same launch wave included Nano Banana 2 Lite as a fast, low-cost Gemini image model.
- 2026-07-08: Managed Agents gained major upgrades including background task support, remote MCP and function calling, network credential refresh, and free-tier availability.
- 2026-07-17: Managed Agents added new cost controls, a free tier for broader testing, and scheduling triggers for agent tasks, including cron-style automation and a `max_total_tokens` parameter for pausing and resuming tasks safely.
- 2026-07-31: Gemini Robotics ER 2 launched in the Gemini API and Google AI Studio, with demos emphasizing real-time multi-robot collaboration.
- 2026-08-05: The Gemini API began supporting simultaneous use of Google Maps and Google Search tools with Gemini 3.5 Flash and 3.6 Flash, unlocking richer location-based app workflows.
- 2026-08-13: A follow-up update highlighted that builders can combine Google Maps and Google Search tools with Gemini to create location applications more easily.
- 2026-08-15: Google AI noted that Gemini 3.7 Flash was available in the Gemini API and rolling out to paid users.
Relevance to AI PMs
- Accelerates product experimentation: PMs can use Gemini API to test assistants, search copilots, issue triage flows, media generation features, and autonomous agents without building infrastructure from scratch. This shortens validation cycles for new AI use cases.
- Enables first-party tool grounding: The addition of Google Search and Google Maps tool use is especially useful for PMs designing experiences that require current information, geographic context, or local recommendations. This can improve accuracy and user value for travel, commerce, field operations, and logistics products.
- Supports operational agent design: Managed Agents, background tasks, cron triggers, function calling, and token-based cost controls give PMs concrete levers for defining agent scope, budgeting usage, and turning prototypes into repeatable workflows.
Related
- Google AI Studio / AI Studio: Closely paired with Gemini API as Google’s development environment for trying models, building apps, and launching managed-agent experiences.
- Google / Google AI / Google DeepMind: Parent organizations behind the Gemini model family and platform updates referenced in the newsletter.
- Gemini model variants: Related models include Gemini 3.5 Flash, Gemini 3.6 Flash, Gemini 3.7 Flash, Gemini 3 Pro Preview, Gemini 3.1 Flash Lite, Gemini Embedding 2, Gemini Omni Flash, and Gemini Robotics ER 2.
- Managed Agents: A major capability layer within Gemini API for hosted autonomous workflows, code execution, scheduling, and sandboxed task execution.
- Function Calling / Remote MCP / Background Tasks / File Search: Supporting platform capabilities that make Gemini API more useful for production agent systems.
- Google Search and Google Maps: First-party tools that can now be used together with Gemini in the API, expanding grounded and location-aware product patterns.
- People mentioned: Logan Kilpatrick and Philipp Schmid are recurring public voices associated with announcing and demonstrating Gemini API updates.
- Example implementations: The GitHub Issue Triage Agent and Managed Agents Quickstart illustrate how teams can move from demos to operational agent workflows on the platform.
Frequently asked questions
What is Gemini API?
Google’s API for accessing Gemini models. The newsletter says Gemini 3.7 Flash is available in it and being rolled out to paid users.
What should AI product managers know about Gemini API?
Gemini API is Google’s platform for accessing Gemini models, agents, multimodal features, and first-party tools like Search and Maps. In 2026, the platform expanded quickly with managed agents, background tasks, scheduling, function calling, and cost controls. Support for combining Google Search and Google Maps made Gemini API more relevant for grounded and location-aware applications.
Explore this topic
Newsletter Mentions (26)
“Google AI recapped new AI integrations for the Pixel 11 series, Pixel Watch 5, and Pixel Tag, alongside Gemini 3.7 Flash’s availability in the Gemini API and rollout to paid users.”
#17 𝕏 Google AI recapped new AI integrations for the Pixel 11 series, Pixel Watch 5, and Pixel Tag, alongside Gemini 3.7 Flash’s availability in the Gemini API and rollout to paid users.
“Philipp Schmid says a small Gemini API update now lets builders combine Google Maps and Google Search tools with Gemini to build location apps.”
#5 𝕏 Philipp Schmid says a small Gemini API update now lets builders combine Google Maps and Google Search tools with Gemini to build location apps.
“Logan Kilpatrick announced that the Gemini API now supports using Google Maps and Google Search tools simultaneously with Gemini 3.5 Flash and 3.6 Flash, an update that had long been on the backlog.”
#1 𝕏 Logan Kilpatrick announced that the Gemini API now supports using Google Maps and Google Search tools simultaneously with Gemini 3.5 Flash and 3.6 Flash, an update that had long been on the backlog.
“Logan Kilpatrick launched Gemini Robotics ER 2 in the Gemini API and Google AI Studio, featuring standout multi-robot collaboration demos that highlight its advanced real-time coordination.”
#9 𝕏 Logan Kilpatrick launched Gemini Robotics ER 2 in the Gemini API and Google AI Studio, featuring standout multi-robot collaboration demos that highlight its advanced real-time coordination. Also covered by: @Philipp Schmid , @Logan Kilpatrick , @Philipp Schmid #10 𝕏 LlamaIndex 🦙 launched Parse Gateway, which uses LiteParse’s is_complex to classify each PDF page (scanned, tables, text, images) and route easy pages in-process or hard pages to advanced LlamaParse tiers.
“#5 𝕏 Logan Kilpatrick introduced new cost controls for managed agents, a free tier for everyone to try, and the first scheduling triggers for agent tasks, highlighting weekly improvements in the Gemini API’s managed agents.”
#5 𝕏 Logan Kilpatrick introduced new cost controls for managed agents, a free tier for everyone to try, and the first scheduling triggers for agent tasks, highlighting weekly improvements in the Gemini API’s managed agents. #13 𝕏 Philipp Schmid launched a free tier for Managed Agents in Google AI Studio’s Gemini API, plus two cost-control updates: a max_total_tokens parameter to pause and resume tasks safely and native cron triggers (e.g., “0 9 * * *”).
“Logan Kilpatrick rolled out major updates to Managed Agents in the Gemini API—adding background task support, remote MCP & function calling, and network credential refresh—and now you can try them on the free tier.”
#2 𝕏 Logan Kilpatrick rolled out major updates to Managed Agents in the Gemini API—adding background task support, remote MCP & function calling, and network credential refresh—and now you can try them on the free tier. Also covered by: @Logan Kilpatrick
“Google DeepMind shipped Nano Banana 2 Lite, its fastest, cheapest Gemini Image model, and rolled out Gemini Omni Flash via the Gemini API and Google AI Studio to enable high-quality video generation and editing.”
Google AI unveiled Gemini Omni, Flash, Nano, and Banana 2 Lite—a suite of multimodal models designed for rapid idea exploration and scalable visual concept creation. Also covered by: @Logan Kilpatrick , @Philipp Schmid , @Google AI #8 𝕏 Google DeepMind shipped Nano Banana 2 Lite, its fastest, cheapest Gemini Image model, and rolled out Gemini Omni Flash via the Gemini API and Google AI Studio to enable high-quality video generation and editing. Also covered by: @Logan Kilpatrick , @Philipp Schmid , @Google AI
“Philipp Schmid launched Managed Agents in the Gemini API, allowing users to spin up autonomous AI agents that reason, write and run code, and manage files inside a hosted Linux sandbox with just one API call.”
#4 𝕏 Philipp Schmid launched Managed Agents in the Gemini API, allowing users to spin up autonomous AI agents that reason, write and run code, and manage files inside a hosted Linux sandbox with just one API call.
“Philipp Schmid built a GitHub Issue Triage Agent using a single curl to the Gemini API.”
#9 𝕏 Philipp Schmid built a GitHub Issue Triage Agent using a single curl to the Gemini API.
“Logan Kilpatrick launched major updates to Google AI Studio and the Gemini API—Gemini 3.5 Flash, managed agents with the antigravity harness, native Android app creation in AI Studio, workspace integrations, and one-click antigravity export.”
#17 𝕏 Logan Kilpatrick launched major updates to Google AI Studio and the Gemini API—Gemini 3.5 Flash, managed agents with the antigravity harness, native Android app creation in AI Studio, workspace integrations, and one-click antigravity export.
Related
AI practitioner credited here with highlighting the public availability of SynthID Detector.
Google's advanced AI research organization. In this newsletter it is mentioned via SynthID Detector and its Gemini live models.
Google AI product lead / developer relations figure frequently associated with Google’s model launches and ecosystem updates.
Google’s research organization, referenced for a clinical evaluation of its medical AI system AMIE.
Google’s AI assistant/model family used here as an enterprise work agent that can handle knowledge, media, coding, and sub-agent orchestration tasks.
Technology company referenced as the place where John Provine previously built evaluation systems. Relevant here as a source of product experimentation rigor.
Google’s AI application builder and workflow environment. Here it is noted for GitHub repository import and bidirectional sync, which matters for AI product workflows and developer experience.
Google’s AI organization, highlighted here for a satellite prototype and space-based infrastructure experiment. The mention connects foundation-model infrastructure with space hardware and TPUs.
CEO of Google and a key voice behind Gemini updates and Google’s AI product direction.
Google model recommended for OCR and VQA workloads. It is highlighted for speed, cost, and accuracy tradeoffs relevant to PM decision-making.
Google’s environment for building and testing AI features, mentioned in the context of developer program redemption. It is relevant for AI prototyping and developer onboarding.
Google's search product used for web retrieval. In this context it is being exposed as a tool inside Gemini API to support grounded answers and tool-augmented reasoning.
A Gemini model variant that was noted as moving out of preview status.
A research capability embedded into Perplexity Computer as a built-in skill. For PMs, it indicates the packaging of advanced research into agent workflows.
An embedding model powering multimodal file search in the Gemini API. Relevant for PMs designing retrieval, citation, and metadata-aware workflows.
Google's mapping and local search platform. Here it appears as a tool that can be invoked alongside Google Search inside Gemini API workflows.
Stay updated on Gemini API
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free