LLM API for React: what 38 makers' products chose
Among 38 makers' products built with React that we know the LLM API of, OpenAI API leads: 23 of them (61%). Next come Claude (12) and Gemini API (6).
Which provider, and whether to go through a gateway. Going direct to a provider gets its newest models and features first and the lowest latency; a gateway gives you one key and one bill for hundreds of models, with fallbacks when a provider is down, for a small markup or a proxy you run. The code that calls the model — an AI SDK or agent framework — is its own decision.
What makers on React chose
| Option | React products | All makers | Free for | At 10,000 users |
|---|---|---|---|---|
| 23 (61%) | 75% | ~1,000 users | $10/moGPT-6 Luna | |
| 12 (32%) | 26% | ~1,000 users | $10/moClaude Haiku 5.5 | |
| 6 (16%) | 10% | ~360 users | $28/moGemini 3.1 Flash-Lite | |
| 3 (8%) | 4% | ~1,500 users | $6.75/moGPT OSS 20B | |
| 2 (5%) | 2% | — | — | |
| 2 (5%) | 7% | — | — | |
| 1 (3%) | 2% | ~1,700 users | $6.00/moMinistral 3 (3B) | |
| 1 (3%) | 1% | ~110 users | — | |
| 1 (3%) | 2% | — | — | |
| 1 (3%) | 0% | — | — |
Live makers' products with a source for both: that they're built with React, and what they use for LLM API. A product using two options counts in both; not market share. "All makers" is the option's share among every maker's product that made this decision.
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; plans for personal use only, like a non-commercial hobby tier, don't count.
Which to pick, by situation
- You want the strongest general models and the widest ecosystem of examples and integrations
OpenAI API 23 here
Claude 12 here
Gemini API 6 here - Token cost dominates your budget, for example high-volume batch or agent workloads
Groq 3 here
Mistral AI 1 here - You want to try or mix many models with one key and one bill, and fall back when a provider is down
OpenRouter 2 here - You want that routing and spend control but self-hosted, with keys and logs on your servers
LiteLLM 1 here
OpenAI API
Model provider23 React products here (61%). Free up to about 1,000 users. About $10 a month at 10,000 users (GPT-6 Luna).
llms.txtIn Lovable, Replit, RorkBest forThe broadest model lineup — text, images, speech, embeddings — and the largest ecosystem.
Trade-offFrequent model and API changes to keep up with, and no option to run its hosted models elsewhere.
“Our experience building with OpenAI has been nothing short of amazing. Their APIs are not only robust but also easy to use. It made the development process smooth and efficient for us.”
- Its models are strong at code generation, reasoning and creative tasks, often chosen after testing alternatives. 4 sources
- The API is reliable and well-priced as the foundation for production features. 4 sources
- It cut usage on the $200 Pro plan and changed limits, frustrating paying subscribers. 4 sources
- Model quality shifts between releases, including a quickly replaced GPT-6 and quietly tweaked reasoning levels. 4 sources
Status page: 5+ incidents in the last 90 days (its own page, 2026-10-19).
“For the latency-sensitive work, OpenAI fit best.”
LLM APIMaker says so +1 · source ↗“LLM models for development and debugging aid.”
LLM APIMaker says so · source ↗“OpenAI helps us analyze public info super fast and write DMs that actually feel personal.”
LLM APIMaker says so · source ↗“hisper for voice transcription. Unmatched accuracy for audio-to-text.”
LLM APIMaker says so · source ↗“Our experience building with OpenAI has been nothing short of amazing. Their APIs are not only robust but also easy to use. It made the development process smooth and efficient for us.”
LLM APIMaker says so · source ↗“APIs and tools for building AI products”
LLM APIMaker says so · source ↗“The GPT-3 API in 2023 release is the reason we started the company itself!”
LLM APIMaker says so · source ↗“Although Layouts.dev is mostly a software based product, we created the Layouts syntax to fit the needs of davinci, the grandpa of ChatGPT. Thanks to it, models like ChatGPT can create beautiful interfaces without struggling with the complexity of the tech stacks that run them. We still use OpenAI API a ton within the product, and build the editor to be used by humans, but loved by AI.”
LLM APIMaker says so · source ↗“Core to our agent planning and reasoning loops. Enables human-like test creation.”
LLM APIMaker says so · source ↗
Claude
Model provider12 React products here (32%). Free up to about 1,000 users. About $10 a month at 10,000 users (Claude Haiku 5.5).
llms.txtIn Lovable, ReplitBest forCoding, long documents and agent-style tool use.
Trade-offNo image generation or embedding models of its own, so those need a second provider.
“The core LLM driving our product. Sonnet 3.5 and Sonnet 4 have been leading the way, handling the toughest work and making our copilot shine ❤️❤️❤️.”
- It is strong at writing code and powers many code generation and coding agent products. 4 sources
- It stays coherent through long, multi-step reasoning and agent workflows. 4 sources
- Outages are frequent, with uptime below three nines across the API and apps. 4 sources
- API pricing is a large multiple of subscription pricing, making heavy agent use expensive. 3 sources
Status page: 36+ incidents in the last 90 days, 17 major (its own page, 2026-10-19).
“Claude’s long context and solid reasoning made it perfect for generating full-stack Python apps.”
LLM APIMaker says so · source ↗“The core LLM driving our product. Sonnet 3.5 and Sonnet 4 have been leading the way, handling the toughest work and making our copilot shine ❤️❤️❤️.”
LLM APIMaker says so · source ↗“Claude Sonnet is a model we use quite for several of our agents.”
LLM APIMaker says so · source ↗“For our use case Anthropic's Claude is currently the most intelligent model on the planet which is why we use it for the user interactions”
LLM APIMaker says so · source ↗“One of the models power our agent”
LLM APIMaker says so · source ↗“Superb for long-context reasoning and agent supervision.”
LLM APIMaker says so · source ↗“Incredible coding capabilities and ability to work with long context windows.”
LLM APIMaker says so · source ↗“One of the main technologies we use for powering Lovable, even more performant with latest models.”
LLM APIMaker says so · source ↗
Gemini API
Model provider6 React products here (16%). Free up to about 360 users. About $28 a month at 10,000 users (Gemini 3.1 Flash-Lite).
In Lovable, ReplitBest forVery long context and multimodal input, with a free tier to start.
Trade-offFree-tier prompts may be used to improve Google's products, so paid tier is the one for user data.
“Since we use firebase, using Gemini was a no brainer, as it just slots in with our database. Also its pricing is by far the most competitive we've seen.”
- It offers some of the best price-to-performance, with fast, cheap Flash models. 4 sources
- A context window of a million tokens or more handles whole codebases and long documents without extra pipelines. 4 sources
- Getting an API key and paying is confusing, with usage tiers and Google Cloud console hoops. 4 sources
- Models are deprecated abruptly, some without leaving preview or having a replacement. 4 sources
“Secondary/Backup LLM provider for our product.”
LLM APIMaker says so · source ↗“Since we use firebase, using Gemini was a no brainer, as it just slots in with our database. Also its pricing is by far the most competitive we've seen.”
LLM APIMaker says so · source ↗“very helpful for enabling us to make the best router possible!”
LLM APIMaker says so · source ↗“Enhancing our email creation with powerful AI capabilities. Helps us generate better copy, images, and designs to create truly engaging emails.”
LLM APIMaker says so · source ↗“Powers multimodal understanding and screenshot interpretation across complex UI flows.”
LLM APIMaker says so · source ↗“for sharp, context-aware suggestions”
LLM APIMaker says so · source ↗
Groq
Open models, hosted3 React products here (8%). Free up to about 1,500 users. About $6.75 a month at 10,000 users (GPT OSS 20B).
Best forVery low-latency inference on open models, for real-time features.
Trade-offOnly the open models it chooses to host, and no frontier closed models.
“Super reliable and fast so our users don't have to wait long”
- Inference is extremely fast, enabling real-time voice and agent workflows. 4 sources
- The free tier is generous, with many models to choose from. 3 sources
“Super reliable and fast so our users don't have to wait long”
LLM APIMaker says so · source ↗“One of the inference providers we use”
LLM APIMaker says so · source ↗“Super speed LLM inference for extracting product titles”
LLM APIMaker says so · source ↗
Azure OpenAI
Through your cloud2 React products here (5%).
MCPBest forOpenAI models inside an Azure account, with regional and EU/US data-zone deployments.
Trade-offMore setup than the OpenAI API (Azure resources, deployments per model), and new models can arrive later.
“It's so convenient to use all the OpenAI functionality right inside Azure.”
“Azure OpenAI cleanly integrates with our serverless app”
LLM APIMaker says so · source ↗“It's so convenient to use all the OpenAI functionality right inside Azure.”
LLM APIMaker says so · source ↗
OpenRouter
Gateway (many providers, one API)2 React products here (5%).
llms.txtIn ReplitBest forTrying many models from many providers with one API key and one bill, without opening an account at each.
Trade-offA fee on top of provider prices, and your traffic and data pass through a third party.
- One API key and OpenAI-compatible endpoint reach hundreds of models from many providers. 1 source
- Switching and comparing models is easy, which speeds up testing cost and quality. 1 source
- Quality varies by underlying provider, so users pin trusted providers to avoid degraded output. 3 sources
- Caching is less effective because requests can switch providers mid-session. 3 sources
Also chosen, and not seen yet
Fewer React products here: Mistral AI (1), Grok API (1), LiteLLM (1), Portkey (1).
Real options for LLM API not seen among these React products yet: DeepSeek.
Who switches, and to what
Public GitHub pull requests whose title says "X to Y", by developers in general, not only on React.
- OpenAI API → Gemini API 178+ pull requests · how they moved
- Gemini API → Groq 152 pull requests · how they moved
- OpenAI API → Claude 127 pull requests · how they moved
- Gemini API → Claude 108+ pull requests · how they moved
- Claude → Gemini API 104+ pull requests · how they moved
- Gemini API → OpenAI API 90+ pull requests · how they moved
Getting LLM API right
Put model calls behind one function in your code so switching providers is a one-line change. Log prompts, responses and cost from day one. Set spending limits on every provider account.
- Shipping with no spending limit or per-user rate limit, so one abusive user or a retry loop runs up the bill overnight.
- Hard-coding one model name across the codebase, so moving to a newer or cheaper model means a search-and-replace and a round of surprises.
- Putting the provider API key in client-side code, where anyone can copy it from the browser.
The rest of the React stack
What makers' React products chose for their other decisions, the most common pick for each:
- Hosting: Vercel 68 of 147
- Transactional Email: SendGrid 64 of 109
- Payments: Stripe 76 of 87
- Database: PostgreSQL 32 of 73
- Web Analytics: Google Analytics 54 of 66
- Product Analytics: PostHog 17 of 37
- Lifecycle Email: Loops 10 of 19
- Workflow Automation: Zapier 15 of 17
Questions
What do most React apps use for LLM API?
Among 38 makers' products built with React that we know the LLM API of, OpenAI API leads: 23 of them (61%). Next come Claude (12) and Gemini API (6).
What does LLM API cost for a React app with 10,000 users?
On our usage model at 10,000 users, OpenAI API comes to about $10 a month (GPT-6 Luna); Claude comes to about $10 a month (Claude Haiku 5.5); Gemini API comes to about $28 a month (Gemini 3.1 Flash-Lite); Groq comes to about $6.75 a month (GPT OSS 20B). Prices are from each vendor's pricing page.
Which LLM API option stays free longest for a React app?
Mistral AI: on our usage model its cheapest plan stays free up to about 1,700 users.
How this is counted: a product is on React when a live-product source says so (the maker, its website, a customer story or a subprocessor list), and the same for its LLM API. How evidence is collected.