Updated

Gemini API

Google's Gemini models via API, with long context and multimodal input.

99 makers' products we track use Gemini API. For LLM API it's 3rd most chosen of 12 options: 99 of the 923 makers' products we know the LLM API of (11%). Among the 256 launched in 2026, 12% chose it, against 8% of those launched in 2024 or earlier. 278 open-source projects also declare it in their code. What makers like most: It offers some of the best price-to-performance, with fast, cheap Flash models. Their most common complaint: Getting an API key and paying is confusing, with usage tiers and Google Cloud console hoops. On GitHub, 367 public pull requests moved projects to Gemini API from tools we list, and 380 moved them away.

Free tierPaid from Pay per token

Profile checked

Works with AI agents:Built into Lovable, Replit
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗
Recent changesFollow Gemini API (RSS)
  • Oct 2026 Gemini API shuts down the deep-research-pro-preview-12-2025 agent on October 23 and now routes gemini-3.7-flash and gemini-3.5-flash to their successors; update the agent and model strings. Takes effect October 23, 2026. source
  • Oct 2026 Gemini API deprecates the gemini-3.1-flash-image model, with no shutdown date yet; move image generation to gemini-nano-banana-2.1. source
  • Sep 2026 Gemini API shuts down the antigravity-preview-05-2026 agent on October 5; its replacement renames the built-in tools and their parameters, so update code that runs tools locally or parses function calls. Takes effect October 5, 2026. source

How makers use Gemini API

Makers' products we track use Gemini API for LLM API (99), most often alongside Next.js (40%), Vercel (30%), Stripe (30%).

What Gemini API is used for

AI App Builders · Hosted app builder →Full-stack web apps and native Android apps (Kotlin, Jetpack Compose) from prompts, with Firestore and Google sign-in set up automatically, two-way GitHub sync and deploys to Cloud Run.Trade-off: Tied to Google's stack — Firebase, Cloud Run, Gemini — and Cloud Run usage is billed once you deploy.
Lovable75v041Bubble38Replit34Softr26Gemini API0Makers' products on each, for AI app builders
Embeddings · General LLM provider →Apps on the Gemini API that want multilingual text embeddings on the same key.Trade-off: General-purpose models, and like any hosted embedding, switching later means re-embedding everything.
Cohere19OpenAI API0Voyage AI0Jina AI0Gemini API0Makers' products on each, for embeddings
Image & Video Generation · First-party model API →Google's image models for generation and editing, and Veo for video, on the same key as Gemini's text models.Trade-off: One vendor's model families only, and video generation is priced per second, so costs rise quickly.
fal20Higgsfield11Replicate10Runway9HeyGen9Gemini API0Makers' products on each, for image & video generation
LLM API · Model provider →Very long context and multimodal input, with a free tier to start.Trade-off: Free-tier prompts may be used to improve Google's products, so paid tier is the one for user data.
OpenAI API736Claude252Gemini API99Groq39Azure OpenAI22Makers' products on each, for LLM API

Gemini API vs the alternatives makers chose

For LLM API, 99 of the 923 makers' products we know the choice of picked Gemini API (11%), behind OpenAI API (80%). Among those launched in 2026 it's 12%.

OptionMakers' products2026 launchesFree forAt 10,000 usersOpen source
OpenAI API736 80%77%~1,000 users$10/mo · GPT-6 LunaNoCompare →
Claude252 27%21%~1,000 users$10/mo · Claude Haiku 5.5NoCompare →
Gemini API99 11%12%~360 users$28/mo · Gemini 3.1 Flash-LiteNo
Groq39 4%3%~1,500 users$6.75/mo · GPT OSS 20BNoCompare →
Azure OpenAI22 2%0%——No
Mistral AI15 2%1%~1,700 users$6.00/mo · Ministral 3 (3B)NoCompare →

For LLM API: how many of the 923 makers' products we know the LLM API of chose each option, and the share among the 256 launched in 2026, since a tool that came first has products from every year, and what each costs at 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

Often paired with

Share of the 99 makers' products on Gemini API that show this choice.

Markets that build with it most

Product Hunt markets where Gemini API is in far more of the stacks we know than across every market (2%).

When to use Gemini API, and when not

Pick Gemini API if

Something else fits better if

  • Token cost dominates your budget, for example high-volume batch or agent workloads: DeepSeek or Groq or Mistral AI.
  • You want to try or mix many models with one key and one bill, and fall back when a provider is down: OpenRouter.
  • You want that routing and spend control but self-hosted, with keys and logs on your servers: LiteLLM.
  • You want a working web app with sign-in and saved data without touching a backend: Lovable or Bolt or Base44.
  • You already have a Next.js project and want generated screens that fit into it: v0.
From each decision's guide, written from what makers' products chose and why.

The Gemini API is Google's developer API for its Gemini models. You send text, images, audio, video or documents and get text back, and related models on the same key generate images, video, speech and embeddings. You use it to add chat, extraction, summarization, multimodal understanding or agents to an app. Keys are created in Google AI Studio.

More about Gemini API

Every API key belongs to a Google Cloud project, and rate limits apply per project, not per key. Google's unified Google GenAI SDK is the supported client, in Python, JavaScript/TypeScript, Go, Java and C#. Google currently recommends its Interactions API for new work, alongside the original generateContent calls, and an OpenAI-compatible endpoint lets existing OpenAI SDK code switch with a new key and base URL.

For a small team the useful parts are a free quota for prototyping, long-context input, function calling and structured output, context caching, and a Batch API for offline jobs. It runs only as Google's hosted service. When you need enterprise controls, the same SDK can target the Gemini Enterprise Agent Platform on Google Cloud.

The main limit is the data terms on free use. On unpaid quota, Google may use your prompts and responses to improve its products, and human reviewers may read them, so free use doesn't suit sensitive data. Outside the EEA, Switzerland and the UK, you have to link billing to avoid this. The API also works only from a listed set of countries.

Gemini API pros and cons

What makers like most: It offers some of the best price-to-performance, with fast, cheap Flash models. Their most common complaint: Getting an API key and paying is confusing, with usage tiers and Google Cloud console hoops.

Pros

  • It offers some of the best price-to-performance, with fast, cheap Flash models. PHPH 2PH 3PH 4
  • A context window of a million tokens or more handles whole codebases and long documents without extra pipelines. PHPH 2PH 3PH 4
  • Native multimodal input covers video, screenshots and audio. PHPH 2PH 3PH 4
  • Google Search grounding is built in for answers that need current facts. HNHN 2HN 3
  • A free tier with no prepayment makes it easy to experiment. PHPH 2HNHN 2
Product Hunt review tags
fast performance17
multimodal capabilities11
Google integration9
high-quality outputs8
large context window7
cost-effective6

Cons and watch-outs

  • Getting an API key and paying is confusing, with usage tiers and Google Cloud console hoops. HNHN 2HN 3HN 4
  • Models are deprecated abruptly, some without leaving preview or having a replacement. HNHN 2HN 3HN 4
  • Pricing docs are unclear, and new models sometimes launch without listed prices. HNHN 2
Product Hunt review tags
inconsistent data6
hallucinations4

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises, with how Product Hunt tags its reviews.

4.9★ from 174 reviews on Product Hunt ↗

What Hacker News says about Gemini API

On Hacker News, 32% of comments about Gemini API recommend it and 7% criticize it: net praise +25%, 4th best liked of 12 tools HN discusses for LLM API.

By year

YearComments choosing it, per monthNet praise
20230.00%
20248.0−29%
202595+36%
2026 (8 mo)131+25%

In their words

  • “Gemini recommended Jellyfin specifically for this situation and coded me something that deletes the videos” HN, May 2026
  • “Gemini and Claude taught me a whole bunch of things about beer” HN, May 2026
  • “both Gemini and GPT are now overwhelmingly a failure as general purpose chatbots” HN, May 2026

Hacker News comments January 2023 to August 2026 that name Gemini API in a sentence like "I use" or "we moved to", Claude read a sample of 100 and the counts scale it to all of them; net praise is comments recommending it minus comments criticizing it, as a share of all comments about it. How it's counted, and how HN compares with makers.

Who switches

More projects move away from Gemini API: 367 pull requests in, 380 out; the most come from OpenAI API and leave for Groq.

Moving to Gemini APIMoving away
Gemini API
OpenAI API → Gemini API178+ PRs
Claude → Gemini API104+ PRs
Groq → Gemini API64 PRs
DeepSeek → Gemini API15 PRs
Mistral AI → Gemini API6 PRs
Gemini API → Groq152 PRs
Gemini API → Claude108+ PRs
Gemini API → OpenAI API90+ PRs
Gemini API → DeepSeek24 PRs
Gemini API → Mistral AI6 PRs

Public pull requests on GitHub since Oct 2024 whose title says "X to Y" — real code changes moving a project from one tool to another, by developers in general.

Apps built with Gemini API

99 makers' products, each linked to the source that shows it, and 278 open-source projects that declare it in their code. The best known on Product Hunt: Scarlett (3,290 followers), MindPal (3,252 followers), Taskade (3,001 followers), Migma AI (2,812 followers), Agentplace.io (2,313 followers). 2 of the makers' products are gone now (domain lapsed, up for sale or taken down); they chose Gemini API while live.

The maker says so 89Subprocessor list 10Declared in code 279How evidence is collected →
giselle
giselleGiselle is an open-source tool for building and running AI workflows in a visual node ed…

“Google's Gemini models bring unmatched context, multimodal, and image generation capabilities to Giselle. With a 1M token context window, our workflows can process entire codebases, long documents, and even video content. From Gemini 2.5 Flash Lite for fast free-tier tasks, to Gemini 2.5 Flash and Pro for balanced and advanced reasoning, Gemini 3 Pro and Flash for the most demanding agentic workflows, and Gemini 2.5 Flash Image for native image generation — we leverage the full Gemini family. Google Search Grounding keeps responses current, while native multimodal support handles text, images, audio, and video seamlessly. Thank you for pushing the boundaries of AI capability!”

LLM APIMaker says so +1 · source ↗
Slashy
SlashyAI email client that triages the inbox and drafts replies in your voice, connected to ca…

“Gemini's long context window is genuinely useful for Slashy's inbox summarization features. When a user has a sprawling email thread or needs their whole inbox triaged at once, Gemini handles the volume without chunking hacks. It's a powerful complement to our other models.”

LLM APIMaker says so · source ↗
MindPal
MindPalMindPal is a no-code platform for turning a person's expertise into AI agents and multi-…

“Shoutout to Gemini for helping power the AI intelligence behind our voice-agent experience.”

LLM APIMaker says so · source ↗
Human Behavior
Human BehaviorHuman Behavior is a product analytics tool whose SDK records events, errors and session…

“The vision model that actually watches session replays”

LLM APIMaker says so · source ↗
GoMarble
GoMarbleAI agent for Paid Media Teams

“Any ad analysis in incomplete without Gemini input. Advanced creative and research capabilities.”

LLM APIMaker says so · source ↗
Youkti
YouktiFinds who's ready to buy, then tells you what to do next

“Fast tool selection, intent classification, signal categorization”

LLM APIMaker says so · source ↗
FirstQuadrant
FirstQuadrantMaximize B2B sales with human-centered AI

“Gemini brings another layer of intelligence to FirstQuadrant. Its unique capabilities expand the boundaries of what our AI can do.”

LLM APIMaker says so · source ↗
RunLLM
RunLLMAI that doesn’t just respond—it resolves

“Gemini is arguably one of the top foundation models and with the most upside. They're executive incredibly well. Especially strong with coding and multi-modal inputs. A great model to keep in our multi-agent toolbox.”

LLM APIMaker says so · source ↗
Migma AI
Migma AIMigma AI generates marketing email campaigns that match your brand, audience and calenda…

“Enhancing our email creation with powerful AI capabilities. Helps us generate better copy, images, and designs to create truly engaging emails.”

LLM APIMaker says so · source ↗
Jinna.ai
Jinna.aiThe AI-native Business OS for solopreneurs that runs itself

“It scales her thinking, memory, and learning — the real infrastructure for her Brain”

LLM APIMaker says so · source ↗
Vouch
VouchBetter than your ATS, meet your hiring assistant

“A top tier AI model thats perfectly balanced for speed, price and quality. Also love the rest of the Google Gemini models!”

LLM APIMaker says so · source ↗
Agentplace.io
Agentplace.ioAI agents that serve your customers

“Multimodal models for responsive AI experiences Gemini helps support fast, capable, and multimodal interactions across the Agentplace platform.”

LLM APIMaker says so · source ↗
Konfide
KonfideAI Agents with a human expert for hire

“Powers all agent conversations on Konfide. Fast, cost-effective, handles unlimited concurrent chats. Every user message goes through Gemini. Chose it for speed and quality at scale.”

LLM APIMaker says so · source ↗
Nautis
NautisThe AI-native Operating System for founders.

“Expanded our multi-model AI capabilities with strong contextual understanding. It helped us explore richer AI workflows across planning, research, and execution.”

LLM APIMaker says so · source ↗
Gro
GroThe best way to prospect and sell with AI

“We chose Gemini 3 for thegro.ai because we needed more than text generation — we needed reasoning. Across real outbound workflows (lead research, prioritization, structured outputs, and human-sounding outreach), Gemini consistently handled long context and multi-step logic better than the alternatives we tested. It gave us strong performance, predictable formatting for Gro IQ, and a cost profile that makes scaling a self-serve AI Sales Co-Pilot viable. For us, it wasn’t about hype — it was about building on a foundation that thinks clearly at scale.”

LLM APIMaker says so · source ↗
n8nChat
n8nChatn8nChat is a Chrome and Firefox extension that builds, edits and debugs n8n workflows fr…

“Google's Gemini models provide excellent performance at competitive pricing, offering our users a cost-effective option for workflow generation. What sets Gemini apart is its 2M token context window that allows for ingesting extensive documentation and workflow history, plus its strong structured output capabilities that help generate precise node configurations.”

LLM APIMaker says so · source ↗
Nerve
NerveGone · site taken down on its host, Oct 2026AI Chief of Staff that does your actual work

“We use a combination of OpenAI, Claude, and Gemini models under the hood”

LLM APIMaker says so · source ↗
Warestack
WarestackEngineering delivery governance for GitHub organizations

“Gemini's extensive token window makes it our go-to solution for one-shot analysis, enabling efficient and precise insights without the need for iterative processing.”

LLM APIMaker says so · source ↗
Warp
WarpOpen-source terminal for macOS, Linux and Windows with built-in coding agents, command b…

“Gemini is a powerful option in Oz for teams that want access to Google’s latest models and infrastructure. Its strengths in multimodal understanding and fast iteration make it a compelling choice for certain agent workflows, and we like giving developers the flexibility to pick the right model for the job.”

LLM APIMaker says so · source ↗
Mina
MinaYour AI Teammate now responds and executes during your calls

“Powering next-generation AI experiences with multimodal intelligence and contextual understanding.”

LLM APIMaker says so · source ↗
Propane
PropaneAutomatic customer context for product teams and agents

“We do not rely on one model, and we see Gemini has its great benefits on some use cases versus other models of them.”

LLM APIMaker says so · source ↗
Taskade
TaskadeOne prompt. One app. One living workspace for teams.

“Gemini pairs naturally with Taskade Genesis. It excels at perception and structure, giving Genesis apps sharper understanding of documents, images, and real-world context.”

LLM APIMaker says so · source ↗
Userology AI
Userology AIThe AI user research agent for busy product teams

“We tap Gemini 2.5 when we need strong multi-modal understanding and cross-checking of insights, using it alongside other models so Userology’s reports are more robust than any single-model stack.”

LLM APIMaker says so · source ↗
Fume
FumeGet Playwright tests from a Loom video

“The native video understanding is what enabled us to build this brand new UX!”

LLM APIMaker says so · source ↗
Genpire
GenpireMake Real Products with AI, literally.

“Part of our multi-model stack. Great creative and reasoning capabilities — especially strong for certain ideation and understanding tasks.”

LLM APIMaker says so · source ↗
Kanbanq
KanbanqProject management. Simply done. For small teams & indies

“Since we use firebase, using Gemini was a no brainer, as it just slots in with our database. Also its pricing is by far the most competitive we've seen.”

LLM APIMaker says so · source ↗
Doraverse
DoraverseThe Secure All-in-One AI Platform for Work

“Another key model in our AI toolkit. Valued for its fast, well-rounded performance across everyday tasks.”

LLM APIMaker says so · source ↗
EmailTemple
EmailTempleThe AI studio for on-brand emails and whole sequences

“The model that does the actual work. Gemini 3 Pro generates every template EmailTemple ships — full HTML, ESP-native, brand-aware. Tested every major frontier model against side-by-side outputs. Gemini won on structural soundness and instruction-following inside long system prompts. Long context made the multi-document architect prompts possible.”

LLM APIMaker says so · source ↗
Greta
GretaGreta is an AI app builder that generates an app's UI, backend and logic from a plain-la…

“Gemini supported parts of the coding and reasoning workflows that power Greta. Its strong multimodal capabilities make it a great engine for building full-stack apps through natural language.”

LLM APIMaker says so · source ↗

Open source: a project that declares Gemini API as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

112 of the 187 open-source products built with Gemini API that were worked on in the last 180 days keep instruction files for coding agents — 60%, against 53% of all the projects we read. AGENTS.md is in 84, CLAUDE.md in 64.

1,144words in the median file
npmthe package manager most named, in 24 of 99 files
71%say how to test a change
Named more in these files than in other projects' — in how many of the 99:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to Gemini API

All alternatives by situation →

Further reading

Questions makers ask about Gemini API

Is Gemini API good for production?

99 makers' products we track run on it, and 2 of them have since gone (the product, not necessarily because of Gemini API). On GitHub, 367 public pull requests moved projects to Gemini API from tools we list, and 380 moved them away. The watch-out makers raise most: Getting an API key and paying is confusing, with usage tiers and Google Cloud console hoops.

What is Gemini API used for?

Google's Gemini models via API, with long context and multimodal input. Makers' products we track use it for LLM API (99).

What are the pros and cons of Gemini API?

Pros makers name: It offers some of the best price-to-performance, with fast, cheap Flash models. A context window of a million tokens or more handles whole codebases and long documents without extra pipelines. Native multimodal input covers video, screenshots and audio. Cons: Getting an API key and paying is confusing, with usage tiers and Google Cloud console hoops. Models are deprecated abruptly, some without leaving preview or having a replacement. Pricing docs are unclear, and new models sometimes launch without listed prices.

What are the alternatives to Gemini API?

For LLM API, the other options makers' products we track chose most are OpenAI API (736), Claude (252), Groq (39), Azure OpenAI (22), Mistral AI (15). Each alternative, with the situation it fits, is on the Gemini API alternatives page.

Is Gemini API still popular with new products?

More than before: among the 256 makers' products launched in 2026 that made the LLM API choice, 12% chose Gemini API, against 8% of the 316 launched in 2024 or earlier.

How much does Gemini API cost per month?

At 10,000 users, Gemini API costs $28 a month on the cheapest plan that fits (Gemini 3.1 Flash-Lite), from its pricing page.

Do developers switch to or away from Gemini API?

On GitHub, 367 public pull requests moved projects to Gemini API from tools we list, most from OpenAI API (178), Claude (104), Groq (64); 380 moved them away, most to Groq (152), Claude (108), OpenAI API (90).

When should you use Gemini API?

You want the strongest general models and the widest ecosystem of examples and integrations (LLM API). You already use OpenAI or Gemini for text and want no new vendor (embeddings). You already use OpenAI or Gemini and want image generation and editing on the same key (image & video generation). Your product generates video from text or images (image & video generation). Something else fits better if: Token cost dominates your budget, for example high-volume batch or agent workloads, pick DeepSeek or Groq or Mistral AI; you want to try or mix many models with one key and one bill, and fall back when a provider is down, pick OpenRouter.

Does Google use my API prompts to train or improve its models?

It depends on whether you're paying. On unpaid quota, Google may use prompts and responses to improve its products, and human reviewers may see them. On paid use (a project with active billing), it doesn't use them for that and logs them only for a limited time to detect abuse. source ↗

Can I use the free tier for an app with users in Europe?

No. If your app serves users in the EEA, Switzerland or the UK, the terms require Paid Services. For developers in those regions, free use is also treated under the paid data terms. source ↗

Is the Gemini API available in every country?

No. You can only use it from the countries on Google's available-regions list, and mainland China and Hong Kong aren't on it. source ↗

How do rate limits work?

Limits apply per project, not per API key. They are measured in requests per minute, tokens per minute and requests per day, and the daily quota resets at midnight Pacific time. Linking billing and spending more moves the project up tiers automatically, and paid tiers also have a rolling 10-minute spend limit. source ↗

Can I use the OpenAI SDK with Gemini?

Yes. Point the OpenAI Python or JavaScript library at Google's OpenAI-compatible base URL and use a Gemini API key. If you aren't already on the OpenAI libraries, Google recommends calling the Gemini API directly. source ↗

Is there a cheaper mode for bulk jobs?

Yes. Batch Mode processes requests asynchronously at half the standard price, with a target turnaround of 24 hours, though most batches finish much sooner. source ↗

Which languages have an official SDK?

The Google GenAI SDK covers Python, JavaScript/TypeScript, Go, Java and C#. Google has called it generally available and the recommended way to call the API. source ↗

When should I use the Enterprise Agent Platform instead?

Google says most developers should use the Gemini Developer API and switch only when they need enterprise controls from Google Cloud. Both are reachable through the same GenAI SDK, so switching is mostly a matter of client configuration. source ↗

Is Gemini API free?

Yes — there is a free tier a small product can run on; paid use starts at Pay per token. source ↗

Is Gemini API open source or self-hostable?

Not open source, and hosted only.

Can AI coding agents work with Gemini API?

Lovable, Replit set it up natively.

Who uses Gemini API?

99 makers' products we track, each with a source, and 278 open-source projects declare it in their code. The best known of them on Product Hunt: Scarlett (3,290 followers), MindPal (3,252 followers), Taskade (3,001 followers), Migma AI (2,812 followers), Agentplace.io (2,313 followers). source ↗