DeepSeek vs OpenAI API
Of the 987 makers' products we know the LLM API of, 736 chose OpenAI API (75%) and 11 DeepSeek (1%); 6 use both. Among the 281 launched in 2026, DeepSeek is in 0% and OpenAI API in 70%, against 1% and 82% of those launched in 2024 or earlier. At our calculator's default usage, DeepSeek comes to $27 a month and OpenAI API $10, at list prices. On GitHub, 16 public pull requests moved projects from DeepSeek to OpenAI API, and 21 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.
OpenAI APIModel providerllms.txtIn Lovable, Replit, RorkWhich 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 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
| Used by | 11 makers' products · 25 open-source projects | 736 makers' products · 596 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 2024 | 21 from OpenAI API | 16 from DeepSeek |
| Downloads | 2.5M/wk5.1× vs npm | 37.4M/wk+60% vs npm |
| Pricing | Pay per token from a prepaid balance; off-peak hours are half price. · paid from Pay per token | Pay per token. · paid from Pay per token |
| Free tier | No | No |
| Open source | No | No |
| Incidents, 90 daysfrom its status page | no public status feed | 5+ |
Which makers on your framework pick
Makers' products built with each framework that chose either one, for LLM API.
| Framework | |||
|---|---|---|---|
| 5 | 222 | All 301 Next.js products' picks → | |
| 0 | 23 | All 38 React products' picks → | |
| 0 | 17 | 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 | 88% 58 | 66 |
| 2023 | 3% 1 | 78% 29 | 37 |
| 2024 | 0% 0 | 80% 178 | 222 |
| 2025 | 3% 7 | 70% 190 | 273 |
| 2026 | 0% 1 | 70% 197 | 281 |
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).
The numbers, plan by plan
| Input tokens per month | DeepSeek | OpenAI 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.
- Talk to any OpenAI-compatible server next to DeepSeek: Ollama, llama.cpp, LM Studio, vLLM or a cloud service of your ownmike13kohler/OpenGhost · 2026-09-29
- feat(llm): swap the chat models from OpenAI to DeepSeekMetnmatEnergy/METNMAT-chatbot · 2026-09-17
- Switch from OpenAI to DeepSeek API and add new articletangyuan233/clip · 2026-09-05
- Switch ICP scorecard assist from OpenAI to DeepSeekhamdi0712/spine-scale-crm · 2026-08-07
- Migrate the PR reviewer from codex/OpenAI to DeepSeekbrandon-fryslie/slopspot-paste · 2026-07-01
- Switch RAG chat LLM from OpenAI to DeepSeektaashchikosi/AI_Portfolio_Projects · 2026-06-13
- Enhance OpenAI-compatible chat clients to DeepSeek paritynvdigitalsolutions/mcp-ai-wpoos · 2026-06-09
- Switch tutor status-draft from OpenAI to DeepSeek V4 Flashzakaria-bennis/Karman-Prep · 2026-05-31
- feat: switch AI provider from OpenAI to DeepSeekNikNik516-1/tg-sales-bot · 2026-05-28
- Switch from OpenAI to DeepSeek APINESYF1KSTORE/FEENDY-POST-MAKER · 2026-05-22
- OLS-4315 - move from deepseek to openai on bedrock and update openai modelsopenshift/lightspeed-service · 2026-09-30
- fix(deepseek): default to OpenAI Chat Completions instead of Responses APIdiegosouzapw/OmniRoute · 2026-09-21
- fix: preserve imageIncapable overrides and migrate DeepSeek preset to OpenAIringotypowriter/yachiyo · 2026-06-18
- chore: switch LLM provider from DeepSeek to OpenAI (gpt-4o-mini)pau-vega/parrot-ai · 2026-06-17
- feat: implement DeepSeek tool call parsing and conversion to OpenAI f…skymoonsun/model-maestro · 2026-04-30
- Migrate effort estimator LLM integration from DeepSeek to OpenAI Chat Completions2025ag05127-blip/effort-estimator · 2026-04-21
- fix(providers): switch DeepSeekProvider from deepseek SDK to OpenAI c…semantica-agi/semantica · 2026-04-18
- Switch AI integration from DeepSeek to OpenAI ChatGPT and update UI messagingantonioreinoespiritual-ux/prueba_centro_experimental · 2026-02-06
- Refactor: migrate DeepSeek client to use OpenAI libraryVitalyRS/TelegaAutoPublishNEWS · 2025-11-04
- Remove DeepSeek references and migrate to OpenAIhenribesnard/harena · 2025-08-20
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
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.
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.
We use variety of OpenAI models (o1, 4o, 4o-mini) and leverage their multi-modal and fine-tuning capabilities to enable multi-step categorization and other domain specific workflows.
Loved and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.
- 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
Who uses each
What makers pair each with
Neither quite right?
See the whole LLM API decision →Questions
DeepSeek or OpenAI API: which do makers choose?
Of the 987 makers' products we know the LLM API of, 736 chose OpenAI API (75%) and 11 DeepSeek (1%); 6 use both. Among the 281 launched in 2026, DeepSeek is in 0% and OpenAI API in 70%, against 1% and 82% of those launched in 2024 or earlier. At our calculator's default usage, DeepSeek comes to $27 a month and OpenAI API $10, at list prices. On GitHub, 16 public pull requests moved projects from DeepSeek to OpenAI API, and 21 the other way. Choose DeepSeek if token cost dominates your budget, for example high-volume batch or agent workloads; choose OpenAI API if you want the strongest general models and the widest ecosystem of examples and integrations.
Can you use DeepSeek and OpenAI API together?
6 makers' products we track use both, often one replacing the other or each for a different part of the product: Shipable AI by CNTXT AI, Webhound, Blink.new, Chat Data, Genstore.ai and others.
When should I pick DeepSeek over OpenAI API?
Pick DeepSeek if: Token cost dominates your budget, for example high-volume batch or agent workloads.
When should I pick OpenAI API over DeepSeek?
Pick OpenAI API if: You want the strongest general models and the widest ecosystem of examples and integrations.
Which is cheaper, DeepSeek or OpenAI API?
At input tokens 50 million tokens, output tokens 10 million tokens: DeepSeek $27/mo (deepseek-flash), OpenAI API $10/mo (GPT-6 Luna), at list prices.
How do DeepSeek and OpenAI API compare in 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). Cheapest usable plan at each scale, at list prices.
Are people switching from DeepSeek to OpenAI API?
Public GitHub pull requests since 2024-10-02: 16 from DeepSeek to OpenAI API, 21 from OpenAI API to DeepSeek.
