How Makers Build
Check my stackPlan my stack
Menu

DeepSeek vs Gemini API

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.

DeepSeekModel provider
Gemini APIModel providerIn Lovable, Replit
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

Which fits you

Choose DeepSeek if
  • 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.

Choose Gemini API if
  • 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

DeepSeekGemini API
Used by11 makers' products · 24 open-source projects99 makers' products · 227 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 202424 from Gemini API15 from DeepSeek
Downloads1.9M/wk4.9× vs npm19.2M/wk6.5× vs npm
PricingPay per token from a prepaid balance; off-peak hours are half price. · paid from Pay per tokenFree tier with rate limits; pay per token. · paid from Pay per token
Free tierNoYes
Open sourceNoNo

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).

$0$100$500$1,000$2,0001510501005001k5k
Gemini APIDeepSeekx: input tokens per month (million tokens), other usage scaled with it · cheapest usable plan at each point, list prices · try your own numbers
The numbers, plan by plan
Input tokens per monthDeepSeekGemini 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.

Gemini API → DeepSeek24 PRs
All matching pull requests on GitHub ↗
DeepSeek → Gemini API15 PRs
All matching pull requests on GitHub ↗

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.

On DeepSeek
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.
IFTTT, the makerSep 2026 ↗
DeepSeek Chat serves as our reliable foundation for basic content creation tasks. Its efficient performance and consistent output quality make it perfect for handling straightforward development requests.
MGX (Now Atoms), the makerSep 2026 ↗
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.
Weavable, the makerSep 2026 ↗
4 more on the DeepSeek page →
On Gemini API
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.
Konfide, the makerSep 2026 ↗
Gemini gives us another strong option for routing complex tasks. Fast response times and competitive pricing mean we can offer our customers more flexibility in how their automations run.
Logic, Inc., the makerSep 2026 ↗
Saturn uses Gemini for structured data extraction from Japanese government filings (EDINET, gBizINFO). Best cost-performance ratio for Japanese language processing at scale.
Saturn, the makerSep 2026 ↗
67 more on the Gemini API page →

Loved and watch-outs

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.

DeepSeek
Most loved
  • It delivers strong reasoning at a small fraction of frontier model prices. PHPH 2HNHN 2
  • Recent Flash models handle real coding work in agent harnesses close to frontier models. HNHN 2HN 3HN 4
  • It has fewer guardrails, so it helps with security and malware analysis other models refuse. HNHN 2HN 3HN 4
Watch-outs
  • It burns many thinking tokens, so cost per finished task can exceed cheap per-token prices. HNHN 2HN 3HN 4
  • It hallucinates, ignores instructions and struggles with end-to-end builds that frontier models finish. HNHN 2HN 3HN 4
On Product Hunt: 4.9★, 53 reviews · mentioned most: deep thinking ability, supports coding tasks, handles complex tasks · complaints: slow performance, not as good as ChatGPT
Gemini API
Most loved
  • 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
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
On Product Hunt: 4.9★, 167 reviews · mentioned most: fast performance, multimodal capabilities, Google integration · complaints: inconsistent data, hallucinations

Who uses each

DeepSeek11 makers' products
Genstore.aiIFTTTMGX (Now Atoms)Read & Give by BonoShipable AI by CNTXT AIWeavableWebhoundBlink.newChat DataBrowser UseCaptioner
Gemini API99 makers' products
1752vc Pitch Deck Analyzer8baseAccorataAgentplace.ioAppear on AIAskiva AIAsmi AIAutomaticallBookmarkjar ®BriefyBuilt for DevsCiro+87 more
Used by both — often one replacing the other, or each for a different part of the product
WebhoundBlink.new

What makers pair each with

With DeepSeek
Frontend Framework
Transactional Email
Hosting
Database
With Gemini API
Frontend Framework
Transactional Email
Database
Hosting

Neither quite right?

See the whole LLM API decision →
OpenAI APIModel providerThe broadest model lineup — text, images, speech, embeddings — and the largest ecosystem.vs DeepSeek →vs Gemini API →
ClaudeModel providerCoding, long documents and agent-style tool use.vs DeepSeek →vs Gemini API →
GroqOpen models, hostedVery low-latency inference on open models, for real-time features.vs Gemini API →
Mistral AIModel providerA European provider whose API covers chat, coding, OCR and speech models.vs DeepSeek →vs Gemini API →
OpenRouterGateway (many providers, one API)Trying many models from many providers with one API key and one bill, without opening an account at each.
LiteLLMGateway (many providers, one API)Running your own OpenAI-compatible proxy in front of your own provider keys, with retries, routing and per-key budgets.