How Makers Build
Check my stackPlan my stack
Menu

DeepSeek vs OpenAI 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
OpenAI APIModel providerllms.txtIn 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 OpenAI API if
  • You want the strongest general models and the widest ecosystem of examples and integrations

Use it whenYou want one account that covers text, images, speech and embeddings, with the most examples to copy from.

Trade-offFrequent model and API changes to keep up with, and no option to run its hosted models elsewhere.

At a glance

DeepSeekOpenAI API
Used by11 makers' products · 24 open-source projects734 makers' products · 481 open-source projects
Cost at default usageinput tokens 50 million tokens, output tokens 10 million tokens$27/mo deepseek-flash$10/mo GPT-6 Luna
Moved to it on GitHubpull requests since Oct 202423 from OpenAI API16 from DeepSeek
Downloads1.9M/wk4.9× vs npm34.1M/wk+61% vs npm
PricingPay per token from a prepaid balance; off-peak hours are half price. · paid from Pay per tokenPay per token. · paid from Pay per token
Free tierNoNo
Open sourceNoNo
Incidents, 90 daysfrom its status pageno public status feed25+ (4 major)

Cost as you grow

At 1M tokens OpenAI API costs less ($0.20 vs $0.54); and still does at 5B tokens ($1,000 vs $2,700).

$0$100$500$1,000$2,0001510501005001k5k
OpenAI 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 monthDeepSeekOpenAI API
1$0.54 deepseek-flash$0.20 GPT-6 Luna
5$2.70 deepseek-flash$1.00 GPT-6 Luna
10$5.40 deepseek-flash$2.00 GPT-6 Luna
50$27 deepseek-flash$10 GPT-6 Luna
100$54 deepseek-flash$20 GPT-6 Luna
500$270 deepseek-flash$100 GPT-6 Luna
1,000$540 deepseek-flash$200 GPT-6 Luna
5,000$2,700 deepseek-flash$1,000 GPT-6 Luna

From each vendor's pricing page: DeepSeek, OpenAI API.

Who moves from one to the other

Public pull requests on GitHub since Oct 2024 whose title says "DeepSeek to OpenAI API" or the reverse — real code changes, by developers in general rather than makers only.

OpenAI API → DeepSeek23 PRs
All matching pull requests on GitHub ↗
DeepSeek → OpenAI API16 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 OpenAI API
We use GPT-5.6 to power the Basedash AI data analyst. It's incredibly intelligent and, with the right harness, allows us to rank #1 on BI Bench for solving real-world BI scenarios.
Basedash, the makerSep 2026 ↗
Credit where it’s due: OpenAI’s dev tools made it incredibly easy to prototype and test multiple ideas fast. Still unmatched when you need raw speed, documentation, and flexibility.
Calk AI, the makerSep 2026 ↗
Quven writes subtitles from the audio of a film on the machine of the user. The Whisper models, run locally through whisper.cpp, can do it and the audio never leaves that machine.
Quven, the makerOct 2026 ↗
500 more on the OpenAI 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
OpenAI API
Most loved
  • Its models are strong at code generation, reasoning and creative tasks, often chosen after testing alternatives. PHPH 2PH 3PH 4
  • The API is reliable and well-priced as the foundation for production features. PHPH 2PH 3HN
  • Good docs and a smooth developer experience make integration straightforward. PHPH 2PH 3PH 4
Watch-outs
  • It cut usage on the $200 Pro plan and changed limits, frustrating paying subscribers. HNHN 2HN 3HN 4
  • Model quality shifts between releases, including a quickly replaced GPT-6 and quietly tweaked reasoning levels. HNHN 2HN 3HN 4
  • Models flag or stop midway on legitimate security work. HNHN 2
On Product Hunt: 5.0★, 860 reviews · mentioned most: AI API, AI productivity boost, fast performance · complaints: AI accuracy issues, AI pricing

Who uses each

DeepSeek11 makers' products
Genstore.aiIFTTTMGX (Now Atoms)Read & Give by BonoShipable AI by CNTXT AIWeavableWebhoundBlink.newChat DataBrowser UseCaptioner
OpenAI API734 makers' products
2dto3D8baseAgentplace.ioAgentXAgnost AIAgree.comAI Context FlowAI Form FillAI Game Master- Dungeon RPGAI Santa ClausAI ShadowingAI Test Engineer by BlinqIO+722 more
Used by both — often one replacing the other, or each for a different part of the product
Genstore.aiMGX (Now Atoms)Shipable AI by CNTXT AIWebhoundBlink.newChat Data

What makers pair each with

With DeepSeek
Frontend Framework
Transactional Email
Hosting
Database
With OpenAI API
Frontend Framework
Transactional Email
Hosting
Payments

Neither quite right?

See the whole LLM API decision →
ClaudeModel providerCoding, long documents and agent-style tool use.vs DeepSeek →vs OpenAI API →
Gemini APIModel providerVery long context and multimodal input, with a free tier to start.vs DeepSeek →vs OpenAI API →
GroqOpen models, hostedVery low-latency inference on open models, for real-time features.vs OpenAI API →
Mistral AIModel providerA European provider whose API covers chat, coding, OCR and speech models.vs DeepSeek →vs OpenAI 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.