DeepSeek vs Gemini API
Of the 987 makers' products we know the LLM API of, 99 chose Gemini API (10%) and 11 DeepSeek (1%); 2 use both. Among the 281 launched in 2026, DeepSeek is in 0% and Gemini API in 11%, against 1% and 8% of those launched in 2024 or earlier. At our calculator's default usage, DeepSeek comes to $27 a month and Gemini API $28, at list prices. On GitHub, 15 public pull requests moved projects from DeepSeek to Gemini API, and 24 the other way.
Two model provider options for LLM API. When each fits, what it costs, who moves from one to the other, and what makers who chose it say.
Gemini APIModel providerIn Lovable, ReplitWhich fits you
- Token cost dominates your budget, for example high-volume batch or agent workloads
Use it whenToken cost dominates your budget, for example high-volume batch or agent workloads.
Trade-offServed from China, which matters for some customers' data requirements; peak-hour prices are double off-peak.
- You want the strongest general models and the widest ecosystem of examples and integrations
Use it whenYou feed in whole documents, video or audio, or want to start without paying.
Trade-offFree-tier prompts may be used to improve Google's products, so paid tier is the one for user data.
At a glance
| Used by | 11 makers' products · 25 open-source projects | 99 makers' products · 278 open-source projects |
|---|---|---|
| Cost at default usageinput tokens 50 million tokens, output tokens 10 million tokens | $27/mo deepseek-flash | $28/mo Gemini 3.1 Flash-Lite |
| Moved to it on GitHubpull requests since Oct 2024 | 24 from Gemini API | 15 from DeepSeek |
| Downloads | 2.5M/wk5.1× vs npm | 22.2M/wk4.9× vs npm |
| Pricing | Pay per token from a prepaid balance; off-peak hours are half price. · paid from Pay per token | Free tier with rate limits; pay per token. · paid from Pay per token |
| Free tier | No | Yes |
| Open source | No | No |
Which makers on your framework pick
Makers' products built with each framework that chose either one, for LLM API.
| Framework | |||
|---|---|---|---|
| 5 | 40 | All 301 Next.js products' picks → | |
| 0 | 6 | All 38 React products' picks → | |
| 0 | 6 | All 27 Astro products' picks → |
New launches vs older products
A tool that came first has products from every year since, so its total runs ahead. Here is what products launched each year chose, as a share of those that made the LLM API decision (by the year they launched on Product Hunt).
| Launched | Products | ||
|---|---|---|---|
| 2022 or earlier | 2% 1 | 8% 5 | 66 |
| 2023 | 3% 1 | 8% 3 | 37 |
| 2024 | 0% 0 | 8% 18 | 222 |
| 2025 | 3% 7 | 14% 39 | 273 |
| 2026 | 0% 1 | 11% 30 | 281 |
Cost as you grow
At 1M tokens DeepSeek costs less ($0.54 vs $0.55); and still does at 5B tokens ($2,700 vs $2,750).
The numbers, plan by plan
| Input tokens per month | DeepSeek | Gemini API |
|---|---|---|
| 1 | $0.54 deepseek-flash | $0.55 Gemini 3.1 Flash-Lite |
| 5 | $2.70 deepseek-flash | $2.75 Gemini 3.1 Flash-Lite |
| 10 | $5.40 deepseek-flash | $5.50 Gemini 3.1 Flash-Lite |
| 50 | $27 deepseek-flash | $28 Gemini 3.1 Flash-Lite |
| 100 | $54 deepseek-flash | $55 Gemini 3.1 Flash-Lite |
| 500 | $270 deepseek-flash | $275 Gemini 3.1 Flash-Lite |
| 1,000 | $540 deepseek-flash | $550 Gemini 3.1 Flash-Lite |
| 5,000 | $2,700 deepseek-flash | $2,750 Gemini 3.1 Flash-Lite |
From each vendor's pricing page: DeepSeek, Gemini API.
Who moves from one to the other
Public pull requests on GitHub since Oct 2024 whose title says "DeepSeek to Gemini API" or the reverse — real code changes, by developers in general rather than makers only.
- docs: switch initial LLM provider from Gemini to DeepSeekisseis/yt2column · 2026-09-28
- feat: Switch from Gemini to DeepSeek AIqianhaoq/dota2.ai · 2026-09-03
- Move off Gemini to DeepSeek, and port the missing AI routes to Functionsaalikes/voxartisan · 2026-08-24
- LLM model is switched from Gemini to DeepSeek for Genkit comsuptionbenxgao/certifai-api · 2026-08-23
- refactor: Gemini to DeepSeek 모델 마이그레이션y0ngha/siglens · 2026-08-17
- Drop Gemini and the LLM picker; lock Scout to DeepSeek v4-flash.marginsystems/x-copilot · 2026-08-14
- feat(ai): switch scoring pipeline from Gemini to DeepSeek V4 ProWekhoh/AMZ-Daily-Digest- · 2026-08-13
- Switch LLM provider from Gemini to DeepSeek V4 Flash huthvincent/yt-bilingual-app · 2026-08-12
- Migrate Gemini integrations to DeepSeekMarkYangjiayi/stock_analysis_website · 2026-08-05
- Switch AI provider from Gemini to DeepSeek v4 FlashHeyians/Sistema-de-engajamento-Instagram- · 2026-07-23
- Move the LLM from Azure DeepSeek to Geminitli9181991/dashboard-testing · 2026-09-06
- Switch the agent's model from DeepSeek to GeminiCHATSCD/Shauns-coding-agent · 2026-08-26
- Switch Phase 1 LLM decision from DeepSeek to Gemini APIChiragVenkateshaiah/tessera · 2026-08-17
- feat(llm): write text with DeepSeek, leave every picture to Geminipinnnthreetriples/telebuba · 2026-08-10
- Switch from OCR+DeepSeek to Google Gemini 2.0 Flash vision modelMuhabuki003/PASS · 2026-07-05
- fix: DeepSeek fallback to Gemini + sanitize orphan tool messagesKrisParjaman/wa-webhook-sbsr · 2026-06-30
- Switch chat API from DeepSeek to Google Gemini.kumarsinghaman/Portfolio · 2026-06-20
- feat: switch AI proxy from DeepSeek to Gemini 2.0 Flashjfcyberknight/darkmedia-x_prompt-ai · 2026-06-05
- feat: migrate AI provider from DeepSeek back to Gemini 3.5 FlashDietCokewithSugar/help-me-invest · 2026-05-20
- migrate from deepseek to geminiGilMM27/scrum-master-AI · 2026-04-13
What makers say
Makers on using it for LLM API, from Product Hunt and Starter Story interviews, each linked to the source. Products with a page of their own and fuller notes first.
DeepSeek delivers serious reasoning at a fraction of the cost of comparable models. We chose it because powerful AI shouldn't have a premium price tag attached to every use case.
DeepSeek gives us frontier-level reasoning at a fraction of the cost, which means we can run AI features at scale without watching the meter. Perfect for the high-volume inference paths where every token counts.
Deepseek V4 Pro is the best bang for buck workhorse model out there
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.
Saturn uses Gemini for structured data extraction from Japanese government filings (EDINET, gBizINFO). Best cost-performance ratio for Japanese language processing at scale.
Gemini pairs naturally with Taskade Genesis. It excels at perception and structure, giving Genesis apps sharper understanding of documents, images, and real-world context.
Loved and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.
Who uses each
What makers pair each with
Neither quite right?
See the whole LLM API decision →Questions
DeepSeek or Gemini API: which do makers choose?
Of the 987 makers' products we know the LLM API of, 99 chose Gemini API (10%) and 11 DeepSeek (1%); 2 use both. Among the 281 launched in 2026, DeepSeek is in 0% and Gemini API in 11%, against 1% and 8% of those launched in 2024 or earlier. At our calculator's default usage, DeepSeek comes to $27 a month and Gemini API $28, at list prices. On GitHub, 15 public pull requests moved projects from DeepSeek to Gemini API, and 24 the other way. Choose DeepSeek if token cost dominates your budget, for example high-volume batch or agent workloads; choose Gemini API if you want the strongest general models and the widest ecosystem of examples and integrations.
Can you use DeepSeek and Gemini API together?
2 makers' products we track use both, often one replacing the other or each for a different part of the product: Webhound, Blink.new.
When should I pick DeepSeek over Gemini API?
Pick DeepSeek if: Token cost dominates your budget, for example high-volume batch or agent workloads.
When should I pick Gemini API over DeepSeek?
Pick Gemini API if: You want the strongest general models and the widest ecosystem of examples and integrations.
Which is cheaper, DeepSeek or Gemini API?
At input tokens 50 million tokens, output tokens 10 million tokens: DeepSeek $27/mo (deepseek-flash), Gemini API $28/mo (Gemini 3.1 Flash-Lite), at list prices.
How do DeepSeek and Gemini API compare in cost as you grow?
At 1M tokens DeepSeek costs less ($0.54 vs $0.55); and still does at 5B tokens ($2,700 vs $2,750). Cheapest usable plan at each scale, at list prices.
Are people switching from DeepSeek to Gemini API?
Public GitHub pull requests since 2024-10-02: 15 from DeepSeek to Gemini API, 24 from Gemini API to DeepSeek.
