“Shoutout to OpenAI for powering our brains with GPT—couldn't build magic without you.”
LLM APIMaker says so +2 · source ↗
OpenAI API
API for GPT models: text, images, speech, embeddings and agents.
737 makers' products we track use OpenAI API. For LLM API it's the most chosen of 12 options: 736 of the 923 makers' products we know the LLM API of (80%). Among the 256 launched in 2026, 77% chose it, against 84% of those launched in 2024 or earlier. 596 open-source projects also declare it in their code. What makers like most: Its models are strong at code generation, reasoning and creative tasks, often chosen after testing alternatives. Their most common complaint: It cut usage on the $200 Pro plan and changed limits, frustrating paying subscribers. On GitHub, 223 public pull requests moved projects to OpenAI API from tools we list, and 385 moved them away.
Profile checked
Works with AI agents:llms.txtBuilt into Lovable, Replit, Rork- Oct 2026 OpenAI removes gpt-5.1, gpt-5.3-codex and gpt-5.4-nano from the API on April 1, 2027; move to gpt-6-sol or gpt-6-luna. Takes effect April 1, 2027. source
- Oct 2026 OpenAI removes the tts-1, tts-1-hd and gpt-4o-mini-tts text-to-speech models on January 6, 2027; move to gpt-realtime-2.1-mini. Takes effect January 6, 2027. source
- Sep 2026 OpenAI removes the gpt-5.4-cyber model on October 1; move to the most capable cyber model your account has. Takes effect October 1, 2026. source
How makers use OpenAI API
Makers' products we track use OpenAI API mostly for LLM API (736), then Speech-to-Text & Text-to-Speech (1), most often alongside Vercel (32%), Next.js (30%), Stripe (24%).
What OpenAI API is used for
OpenAI API vs the alternatives makers chose
For LLM API, 736 of the 923 makers' products we know the choice of picked OpenAI API (80%), the most of 12 options. Among those launched in 2026 it's 77%.
| Option | Makers' products | 2026 launches | Free for | At 10,000 users | Open source | |
|---|---|---|---|---|---|---|
| 736 80% | 77% | ~1,000 users | $10/mo · GPT-6 Luna | No | ||
| 252 27% | 21% | ~1,000 users | $10/mo · Claude Haiku 5.5 | No | Compare → | |
| 99 11% | 12% | ~360 users | $28/mo · Gemini 3.1 Flash-Lite | No | Compare → | |
| 39 4% | 3% | ~1,500 users | $6.75/mo · GPT OSS 20B | No | Compare → | |
| 22 2% | 0% | — | — | No | Compare → | |
| 15 2% | 1% | ~1,700 users | $6.00/mo · Ministral 3 (3B) | No | Compare → |
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 737 makers' products on OpenAI API that show this choice.Markets that build with it most
Product Hunt markets where OpenAI API is in far more of the stacks we know than across every market (14%).
When to use OpenAI API, and when not
Pick OpenAI API if
- 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 →
- Voice is a side feature and one vendor matters more than fine control. Speech-to-Text & Text-to-Speech →
- Response delay matters most and you're fine with one model doing the listening and talking. Voice Agents →
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.
- Your users search in many languages, or you want embeddings and a reranker from one API: Cohere or Jina AI.
- Generic embeddings miss the terms in your code, legal or finance documents: Voyage AI.
The OpenAI API gives your backend HTTP access to OpenAI's models: text and code generation, reasoning, image generation and editing, speech-to-text, text-to-speech, realtime voice, embeddings and moderation. It is how you put GPT models inside your own product, billed to your organization rather than to a ChatGPT subscription.
More about OpenAI API
You authenticate with a secret API key that belongs to a project inside an organization; rate limits, spend limits and data settings are set at those two levels. OpenAI recommends the Responses API for new work: one endpoint that can keep conversation state on OpenAI's side (store) and call built-in tools such as web search, file search, code interpreter, computer use and remote MCP servers. The older Chat Completions API is still supported. Official SDKs cover TypeScript/JavaScript, Python, .NET, Java, Go and Ruby, plus an Agents SDK for TypeScript and Python.
For a small team the useful pieces are structured outputs and function calling, a Batch API for offline jobs, prompt caching, fine-tuning, evals, and per-project spend limits and alerts. It runs only as OpenAI's hosted service; eligible customers can pin projects to regions such as the US or EU, and the models are also sold through Microsoft Azure.
The main limit is that the models are closed: you can't self-host them, and your traffic depends on OpenAI's terms, rate-limit tiers and model deprecation schedule.
How OpenAI API itself is built
5 tools, from its own code, website and Product Hunt page.
OpenAI API pros and cons
What makers like most: Its models are strong at code generation, reasoning and creative tasks, often chosen after testing alternatives. Their most common complaint: It cut usage on the $200 Pro plan and changed limits, frustrating paying subscribers.
Pros
- 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
- Whisper gives accurate speech-to-text across many languages. PHPH 2PH 3
Cons and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises, with how Product Hunt tags its reviews.
5.0★ from 872 reviews on Product Hunt ↗What Hacker News says about OpenAI API
On Hacker News, 16% of comments about OpenAI API recommend it and 8% criticize it: net praise +8%, 10th best liked of 12 tools HN discusses for LLM API.
By year
| Year | Comments choosing it, per month | Net praise |
|---|---|---|
| 2023 | 185 | +21% |
| 2024 | 82 | −6% |
| 2025 | 115 | +10% |
| 2026 (8 mo) | 104 | 0% |
In their words
- “I use this default context in ChatGPT and it works pretty well for me” HN, May 2026
- “my OpenAI TAC application lingers in a total limbo” HN, Aug 2026
Hacker News comments January 2023 to August 2026 that name OpenAI API in a sentence like "I use" or "we moved to", Claude read a sample of 199 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.
Reliability and open issues
OpenAI API's status page posted 5+ incidents in the last 90 days, none major.
Incidents on its status page
5+ in the last 90 days · 5+ in the last year- minor Delayed Costs data in the Compliance API Oct 2026
- minor Delayed Costs data in the Compliance API Oct 2026
- minor Errors processing large PDFs in the Responses API Oct 2026
Who switches
More projects move away from OpenAI API: 223 pull requests in, 385 out; the most come from Gemini API and leave for Gemini API.
Gemini API → OpenAI API90+ PRs
- gemini fallback to openai fixesmaximhq/bifrost · 2026-10-02
- Switch LLM backend from Gemini to OpenAI gpt-4o-miniPiSquareLabs/PathShala · 2026-09-30
- perf(gemini): Migrate Gemini to OpenAI formattisfeng/Easydict · 2026-09-29
- fixes foreign-function-call-id issue for fallback from gemini to openaimaximhq/bifrost · 2026-09-29
- Switch the model calls from Gemini to OpenAI gpt-5.4-miniMishaMatcharashvili/trip-io · 2026-09-25
- refactor: migrate AI insights service from Gemini API to OpenAI APITkYaLa34/AI-Investment-Research-Platform- · 2026-09-23
- Switch AI provider from Gemini to OpenAI, add dialogue lessons, fix e…aaryashah1010/Fluentify · 2026-09-22
- migrated from gemini to openai llmmohitgarg196/CodeVitals-AI · 2026-09-21
- Fix Gemini adapter to support OpenAI SDK client formatarvindg4u/APIKeyRotator · 2026-09-20
- Fix Gemini chat model + image fallback to OpenAIfabelanorma3010/How--to-wite--a-fiction-book · 2026-09-05
Claude → OpenAI API88 PRs
- fix: round-trip Claude tool_use to OpenAI tool_callsks1686/peaproxy · 2026-09-27
- Switch receipt AI scan from Claude to OpenAIianselmi/cardmaster · 2026-09-26
- Migrate from Claude to OpenAI API for synthesis toolsarkhash0309/research-paper-intelligence-pipeline · 2026-09-25
- Switch Alora Chat from Claude to OpenAIvaniabhagania/Alora · 2026-09-24
- Migrate all Claude resume tailoring to OpenAIrfahamedansari/job-application-assistant · 2026-09-23
- feat(claude): map output_config.format to OpenAI response_formatrouter-for-me/CLIProxyAPI · 2026-09-23
- feat(claude-boxes): allow codex egress to the OpenAI auth and API hostsLanternfyre/home-lab · 2026-09-22
- [synthmind-bot] Security Researchers Use Anthropic Claude to Hack OpenAI — 2026-09-18administrakt0r/AIautonomousBlogMY · 2026-09-18
- Switch LLM provider from Anthropic Claude to OpenAI GPT-4o.sji-soumik/ai-assessment · 2026-09-11
- fix: clamp Claude Code egress to OpenAI and Gemini (RUN-1515)NeuralTrust/TrustGate · 2026-09-10
Groq → OpenAI API25 PRs
- Switch SAP prompt improver from Groq to OpenAIabhishekashishde-byte/SAP-Brain · 2026-09-22
- refactor: migrate from Groq to OpenAI gpt-5.4-nano for ISL translationkarchit1128/Sanket · 2026-09-22
- Change Groq LLM models: from Llama 3.3 to OpenAI GPTpattames/vet_chatbot_v2 · 2026-09-20
- Changed AI used from groq to openaiReDILABMunich/Helferei · 2026-09-16
- Restore 2026-03-22 QuantSage build and switch AI provider from Groq to OpenAIkabwefrancis13-web/KABWE · 2026-09-15
- fix(groq): migrate deprecated llama models to openai gpt-ossDushmilan/CodeCoach-AI · 2026-08-24
- feat: migrate ForgePair agents from Groq to OpenAIbfrpaulondev/dev-agent-lab · 2026-08-21
- fix(ai): never send Groq catalog ids to OpenAIRevealUIStudio/revealui · 2026-08-18
- Migrate chatbot from Groq to OpenAIhari9255/app_service_demo · 2026-08-10
- Migrate receipt extraction from Groq to OpenAI (gpt-4.1-mini)IlyaShynkevich/grocery-buddy · 2026-08-01
DeepSeek → OpenAI API16 PRs
- 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
Mistral AI → OpenAI API4 PRs
- test: fix Mistral test due to new OpenAI SDK releasedeepset-ai/haystack-core-integrations · 2026-09-01
- Port AI integration from Mistral to OpenAI API; rename Mistral→Chat throughoutLavey/mastra48 · 2026-03-18
- feat: migrate from Mistral to OpenAI gpt-5-nanoLyleW473/NLPGroupCoursework · 2025-12-07
- test: adapt Mistral to OpenAI refactoringdeepset-ai/haystack-core-integrations · 2025-01-02
OpenAI API → Gemini API178+ PRs
- feat(dh): switch listup web search from OpenAI to Geminigrowthhackerssnu/admin · 2026-10-01
- Switch production thumbnails from OpenAI to Geminikevin4relocate/TripCaution · 2026-09-30
- feat: move OpenAI and Google defaults to GPT-6 and Gemini 3tag1consulting/ai-pr-review · 2026-09-29
- Migrate from OpenAI to Google Gemini for embeddings and LLManiilhr/agentic-ai-rag-chatbot · 2026-09-29
- fix: preserve image parts in OpenAI to Gemini responsesmoeacgx/NewAPI-Mao · 2026-09-27
- Updating from OpenAI to Gemini in llm.py following the potential toke…harpand87/banking-support-agent · 2026-09-27
- Switch the assistant LLM from OpenAI to Geministariik/Mia · 2026-09-26
- port(upstream): #4274 - disambiguate colliding tool call ids in openai to geminibloodf/durindoor · 2026-09-25
- feat(gemini): convert OpenAI Embeddings to Gemini embeddingstbphp/gpt-load · 2026-09-25
- Switch AI provider from OpenAI to Google GeminiOricrew/service-scheduler · 2026-09-24
OpenAI API → Claude127 PRs
- Migrate AI provider from OpenAI to Anthropic Claudesawthunaing/stn-job-hunting-dashboard-with-ai · 2026-10-01
- Preserve readable context when switching owned OpenAI to ClaudeJJLiebig/codex · 2026-10-01
- Add OpenAI Codex plugin marketplace to Claude Code project settingsbrandohermoso47-rgb/cliente-vault-web-app · 2026-10-01
- Switch Wardrobe from OpenAI to Claudenjarrar/wardrobe-najeeb · 2026-09-28
- Switch receipt extraction from OpenAI to Claudebelindahbl/receipt-telegram-bot · 2026-09-26
- Switch AI copy from OpenAI to Claude Haiku 4.5fareeha-s/shouldve-walked · 2026-09-26
- Phase 1: Switch AI provider from OpenAI to Anthropic Claudeanfaznil/tabletalk-ai · 2026-09-23
- fix(thinking): route OpenAI and level-based reasoning models to claude-adaptive on Claude endpointshkbulbul/polyrouter · 2026-09-23
- Switch FAQ replies from OpenAI to Anthropic Claudeimranaisolutions/Agentic-Ai · 2026-09-23
- Switch AI provider from OpenAI to Claude, and hand redirects to AJR Core (4.1.0)andrew-ajrwebdesign/ai-seo-assistant · 2026-09-22
OpenAI API → Groq50 PRs
- Switch eval pipeline LLM provider from OpenAI to Groqgsarthakdev/llm-eval-pipeline · 2026-09-15
- Migrate LLM backend from OpenAI GPT-4 to Groq (openai/gpt-oss-120b)Blandskron/pentest-agent · 2026-09-09
- Switch LLM provider from OpenAI to GroqkarMareal1/WhyUs · 2026-09-04
- feat(clips): switch Whisper and chat from OpenAI to Groqasgard02/vyrll · 2026-08-16
- changed from openai to groq because no way I'm paying to openai for a…ubturja/Is-It-For-Real · 2026-08-15
- Revert AI assistant LLM provider from OpenAI back to Groq (free tier)mudone1/Tdislogistics · 2026-08-10
- Swap transcription provider from OpenAI to GroqF-NAN-AI-ENGINEERING-RESIDENCY/compass · 2026-08-03
- Rename OpenAI provider to Groq providerKutlay07/ai-assistant-platform · 2026-07-31
- Task 1 done Migrate completely from OpenAI to GroqQuantumLogicsLabs/RepoMind · 2026-07-27
- Switch AI provider from OpenAI to GroqShiveshDragon/Benefit_Bridge · 2026-07-25
OpenAI API → DeepSeek21 PRs
- 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
OpenAI API → Mistral AI9 PRs
- Migrate runtime from OpenAI to Mistral and add Mistral transports, analyzers and harnessesarnaudconnan-svg/acp-chat · 2026-08-29
- docs: switch LLM provider from Anthropic/OpenAI to MistralBimsara-Yehan/ChemSentry · 2026-08-18
- Migration from openAI to MistralZering-Max/tepsia-chatbot · 2026-08-10
- fix(ai): switch rag-eval from OpenAI to Mistral (credits exhausted)andrelair-platform/minicloud-gitops · 2026-08-02
- Migrate from OpenAI to Mistral, add reliability, idempotency, telemetry, and runbooksAbdulmuiz44/SayReady · 2026-03-21
- fix: switch CI LLM from OpenAI to Mistral MAASrossoctl/rossoctl · 2026-03-03
- fix: add mergeToolResultText for OpenAI provider to fix Mistral tool message orderingRooCodeInc/Roo-Code · 2026-01-13
- change openai to mistral ai as llm apiOscar-Hirsch/newsPortal · 2025-06-19
- Change openAI to Mistral in text about VCsalkem-io/client-web · 2025-03-12
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.
Who uses it
737 makers' products, each linked to the source that shows it, and 596 open-source projects that declare it in their code. The best known on Product Hunt: Writesonic (9,263 followers), D-ID (7,908 followers), Basedash (7,673 followers), BeforeSunset AI (6,066 followers), OpenArt AI (4,649 followers). 26 of the makers' products are gone now (domain lapsed, up for sale or taken down); they chose OpenAI API while live.
“OpenAI is our default LLM provider and a common choice among our users.”
LLM APIMaker says so +1 · source ↗“OpenAI's GPT models power a wide range of Giselle's AI workflows. From GPT-5 nano for quick, cost-effective tasks on our free tier, to GPT-5 mini for balanced everyday use, GPT-5 and GPT-5.1 Codex for complex reasoning and coding agents, and GPT-5.2 for the most demanding challenges — we leverage the full GPT family. The Reasoning Effort parameter lets users fine-tune the balance between speed and depth, while Web Search keeps workflows grounded in real-time information. Thank you for building such a versatile AI platform!”
LLM APIMaker says so +1 · source ↗“OpenAI function calling powers the new evaluation service. Reliability out of the box without any weird outputs!”
LLM APIMaker says so +1 · source ↗“Our LLM features are powered by OpenAI”
LLM APIMaker says so +1 · source ↗“Image 2.0 is just on a next level”
LLM APIMaker says so +1 · source ↗“Supabase AI Assistant leverages the incredible capabilities of OpenAI’s models to deliver intelligent, context-aware assistance for developers.”
LLM APIMaker says so +1 · source ↗“Reliable SOTA AI models.”
LLM APIMaker says so +1 · source ↗“The most reliable foundation model for fast, high-quality copy generation.”
LLM APIMaker says so +1 · source ↗“OpenAI's models are part of our multi-model architecture. We use different models for different tasks within Slashy: some optimized for speed, others for nuance. OpenAI's API reliability and breadth of capabilities made it a natural part of our stack.”
LLM APIMaker says so +1 · source ↗“We use OpenAI to power Plane AI — enabling teams to chat with their projects, write PRDs, dedupe issues, and get instant insights. It’s the brain behind everything smart inside Plane.”
LLM APIMaker says so +1 · source ↗“Provides state-of-the-art LLMs for reasoning and codebase understanding. Powers planning and verification workflows in Traycer.”
LLM APIMaker says so +1 · source ↗“Shoutout to OpenAI for kickstarting the generative AI revolution with ChatGPT! Their groundbreaking work has inspired countless innovations. We're excited to build on their achievements and grateful for their, ahem, "privacy concerns" that helped make our product possible. Proud to have supported OpenAI's models from the start. Here's to advancing AI while keeping data safe!”
LLM APIMaker says so +1 · source ↗“We use OpenAI models for parts of automated scenario generation, evaluation and building some of our pre-defined metrics”
LLM APIMaker says so +1 · source ↗“Among the main LLM provider for power our assistants.”
LLM APIMaker says so +1 · source ↗“Complex analysis, competitive intelligence, deep research”
LLM APIMaker says so +1 · source ↗“Lovely documentation for building on the OpenAI Response API.”
LLM APIMaker says so +1 · source ↗“ChatGPT Atlas is a groundbreaking browser that integrates ChatGPT right into your workflow. The seamless sidebar experience enables quick summarization and analysis of content without switching tabs. It truly feels like having a smart assistant on every page, improving productivity and delivering a more intuitive browsing experience.”
LLM APIMaker says so +1 · source ↗“Great array of models for different purposes, and love the playground for quick exploration”
LLM APIMaker says so +1 · source ↗“Still the most consistent model for high-stakes support answers. GPT-4-turbo gives us control, reliability, and depth — all critical for enterprise use. Most production-ready reasoning and tool use stability.”
LLM APIMaker says so +1 · source ↗“I mean, come on, literally none of this would have been possible without the amazing work that Sam and his team have been doing for years. At this point "having" AI your product is basically OpenAI :)”
LLM APIMaker says so +1 · source ↗“For the latency-sensitive work, OpenAI fit best.”
LLM APIMaker says so +1 · source ↗“We use OpenAI to create our fine-tuned models.”
LLM APIMaker says so +1 · source ↗“We chose OpenAI because it gave us the strongest foundation for AI features that need reliable structured output, not just chat. For FC Tactix, that matters when turning football ideas into usable tactical content inside the product.”
LLM APIMaker says so +1 · source ↗“We use GPT-4 internally for writing copy (like this one!) and in our app to give our users the highest quality of GenAI answers possible”
LLM APIMaker says so +1 · source ↗“One of the best LLMs.”
LLM APIMaker says so +1 · source ↗“Access to powerful language models, including GPT, for tasks like natural language processing, text generation, summarization, translation, and more”
LLM APIMaker says so +1 · source ↗“You can select models from OpenAI to power the AI agents you build on MindPal!”
LLM APIMaker says so · source ↗“Workhorse for a number of underlying services and options.”
LLM APIMaker says so · source ↗“Core to our agentic stack for understanding and writing integration code.”
LLM APIMaker says so · source ↗“OpenAI API make it possible for us to build our realtime voice-to-voice AI chatbot and we cannot find another company which offers the same API service”
LLM APIMaker says so · source ↗“Anthropic is highly integrated into Chat Thing! It's amazing.”
LLM APIMaker says so · source ↗“Every answer PH Ask gives runs through their models.”
LLM APIMaker says so · source ↗“FirstQuadrant wouldn’t be possible without OpenAI models like GPT 4.1 and o3. It's the backbone of many of our AI-driven automations and reasoning flows.”
LLM APIMaker says so · source ↗“This template's AI writing features are built on OpenAI APIs and tools.”
LLM APIMaker says so · source ↗“This model was fine-tuned using GPT-oss-120B as our base!”
LLM APIMaker says so · source ↗“Great all around suite of models for the agent”
LLM APIMaker says so · source ↗“Core to our agent planning and reasoning loops. Enables human-like test creation.”
LLM APIMaker says so · source ↗“We're leveraging OpenAI's powerful models to drive THEO's AI capabilities.”
LLM APIMaker says so · source ↗“The OpenAI API powers our AI features and powers our Slack bot”
LLM APIMaker says so · source ↗“OpenAI stood out for its model quality, reliability, and simple developer experience. It helped us build AI-powered workflows that feel fast, accurate, and genuinely useful for customer support teams.”
LLM APIMaker says so · source ↗“The other LLM API that made it possible for the SWE agent to efficienly use tools, decide steps to be taken, and code geneartion!”
LLM APIMaker says so · source ↗“OpenAI powers both our dictation + Rewrite engine and the LLM brains behind MCP execution. When Saga turns your voice into real GitHub commits or Notion updates, it's OpenAI doing the heavy lifting.”
LLM APIMaker says so · source ↗“More than half of our code is either written by or polished by GPT”
LLM APIMaker says so · source ↗“Melies uses different OpenAI models (o1, 4o, 4o-mini) for AI screenwriting.”
LLM APIMaker says so · source ↗None of these in makers' own words.
Open source: a project that declares OpenAI API as a dependency in its public code — verifiable, but not necessarily a live product.
What its projects tell coding agents
229 of the 382 open-source products built with OpenAI 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 173, CLAUDE.md in 140.
Alternatives to OpenAI API
All alternatives by situation →Further reading
Questions makers ask about OpenAI API
Is OpenAI API good for production?
737 makers' products we track run on it, and 26 of them have since gone (the product, not necessarily because of OpenAI API). Its own status page posted 5+ incidents in the last 90 days; vendors decide what they post there, so this doesn't compare across tools. On GitHub, 223 public pull requests moved projects to OpenAI API from tools we list, and 385 moved them away. The watch-out makers raise most: It cut usage on the $200 Pro plan and changed limits, frustrating paying subscribers.
What is OpenAI API used for?
API for GPT models: text, images, speech, embeddings and agents. Makers' products we track use it for LLM API (736), Speech-to-Text & Text-to-Speech (1).
What are the pros and cons of OpenAI API?
Pros makers name: Its models are strong at code generation, reasoning and creative tasks, often chosen after testing alternatives. The API is reliable and well-priced as the foundation for production features. Good docs and a smooth developer experience make integration straightforward. Cons: It cut usage on the $200 Pro plan and changed limits, frustrating paying subscribers. Model quality shifts between releases, including a quickly replaced GPT-6 and quietly tweaked reasoning levels. Models flag or stop midway on legitimate security work.
What are the alternatives to OpenAI API?
For LLM API, the other options makers' products we track chose most are Claude (252), Gemini API (99), Groq (39), Azure OpenAI (22), Mistral AI (15). Each alternative, with the situation it fits, is on the OpenAI API alternatives page.
Is OpenAI API still popular with new products?
About as much as before: among the 256 makers' products launched in 2026 that made the LLM API choice, 77% chose OpenAI API, against 84% of the 316 launched in 2024 or earlier.
How much does OpenAI API cost per month?
At 10,000 users, OpenAI API costs $10 a month on the cheapest plan that fits (GPT-6 Luna), from its pricing page.
Do developers switch to or away from OpenAI API?
On GitHub, 223 public pull requests moved projects to OpenAI API from tools we list, most from Gemini API (90), Claude (88), Groq (25); 385 moved them away, most to Gemini API (178), Claude (127), Groq (50).
When should you use OpenAI 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). Voice is a side feature and one vendor matters more than fine control (Speech-to-Text & Text-to-Speech). Response delay matters most and you're fine with one model doing the listening and talking (voice agents). 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 OpenAI train its models on what I send through the API?
No, not by default. Data sent to the API has not been used for training since March 1, 2023, unless you explicitly opt in to share it. source ↗
How long does OpenAI keep my prompts and outputs?
By default, abuse-monitoring logs that can include prompts and responses are kept for up to 30 days, and the Responses API stores response objects for at least 30 days unless you set store to false. Zero Data Retention and Modified Abuse Monitoring exist, but they require OpenAI's prior approval. source ↗
Can I keep my data in the EU or another region?
Yes, if you are eligible, which is decided through sales. Data residency is set per project, stores customer content at rest in the chosen region, and in some regions also runs inference there. Non-US regions also require approval for abuse-monitoring controls. source ↗
Can I use it for health data under HIPAA?
Only after signing OpenAI's Business Associate and Healthcare Addendum and having your organization provisioned for it. PHI can then go only through BAA-eligible endpoints; web search with live internet access, for example, isn't covered. source ↗
How do rate limits work for a new account?
Limits apply per organization and per project, not per user, and are measured in requests and tokens per minute and per day. As your total paid spend grows, OpenAI moves you up usage tiers automatically, which raises your limits and your monthly usage cap. source ↗
Is there a cheaper way to run large offline jobs?
Yes. The Batch API takes a .jsonl file of requests, finishes within 24 hours, and costs half as much as the same calls made synchronously. source ↗
Which languages have an official SDK?
JavaScript/TypeScript (Node.js, Deno, Bun), Python, .NET, Java, Go and Ruby. Java and Go are labeled beta, and there are official Agents SDKs for TypeScript and Python. source ↗
Should I build on Chat Completions or the Responses API?
OpenAI recommends Responses for all new projects. It adds built-in tools and optional server-side conversation state, while Chat Completions remains supported. source ↗
Is OpenAI API free?
No permanent free tier; paid use starts at Pay per token. source ↗
Is OpenAI API open source or self-hostable?
Not open source, and hosted only.
Can AI coding agents work with OpenAI API?
It serves an llms.txt docs index; Lovable, Replit, Rork set it up natively.
Who uses OpenAI API?
737 makers' products we track, each with a source, and 596 open-source projects declare it in their code. The best known of them on Product Hunt: Writesonic (9,263 followers), D-ID (7,908 followers), Basedash (7,673 followers), BeforeSunset AI (6,066 followers), OpenArt AI (4,649 followers). source ↗