Updated

Claude

Anthropic's Claude models via API, strong at coding, long documents and tool use.

252 makers' products we track use Claude. For LLM API it's 2nd most chosen of 12 options: 252 of the 923 makers' products we know the LLM API of (27%). Among the 256 launched in 2026, 21% chose it, against 24% of those launched in 2024 or earlier. 345 open-source projects also declare it in their code. What makers like most: It is strong at writing code and powers many code generation and coding agent products. Their most common complaint: Outages are frequent, with uptime below three nines across the API and apps. On GitHub, 253 public pull requests moved projects to Claude from tools we list, and 223 moved them away.

No free tierPaid from Pay per token

Profile checked

Works with AI agents:llms.txtBuilt into Lovable, Replit
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗
Recent changesFollow Claude (RSS)
  • Oct 2026 Claude changed its llm api pricing: Claude Haiku 4.5 plan dropped; new plan Claude Haiku 5.5. At the calculator's typical usage it now costs $10 a month instead of $100. source
  • Oct 2026 Claude API managed agents with limited networking now apply allowed_hosts to web_search and web_fetch, so unlisted hosts are blocked; add every host those tools need to allowed_hosts. source
  • Sep 2026 Claude API retires Claude Sonnet 4.5 (claude-sonnet-4-5-20250929) on November 30, 2026; move to Claude Sonnet 5.5 before then. Takes effect November 30, 2026. source

How makers use Claude

Makers' products we track use Claude for LLM API (252), most often alongside Next.js (49%), Vercel (46%), Stripe (38%).

What Claude is used for

Browser Automation for Agents · Agent library →Letting Claude itself drive a browser or desktop through the API's browser-use and computer-use toolsets, while your application runs the browser and carries out each action.Trade-off: You run the browser or desktop environment yourself; Anthropic notes latency is slow next to a human and recommends a sandboxed VM or container.
Browserbase16Browser Use12Kernel1Skyvern1Browserless1Claude0Makers' products on each, for browser automation for agents
LLM API · Model provider →Coding, long documents and agent-style tool use.Trade-off: No image generation or embedding models of its own, so those need a second provider.
OpenAI API736Claude252Gemini API99Groq39Azure OpenAI22Makers' products on each, for LLM API

Claude vs the alternatives makers chose

For LLM API, 252 of the 923 makers' products we know the choice of picked Claude (27%), behind OpenAI API (80%). Among those launched in 2026 it's 21%.

OptionMakers' products2026 launchesFree forAt 10,000 usersOpen source
OpenAI API736 80%77%~1,000 users$10/mo · GPT-6 LunaNoCompare →
Claude252 27%21%~1,000 users$10/mo · Claude Haiku 5.5No
Gemini API99 11%12%~360 users$28/mo · Gemini 3.1 Flash-LiteNoCompare →
Groq39 4%3%~1,500 users$6.75/mo · GPT OSS 20BNoCompare →
Azure OpenAI22 2%0%——No
Mistral AI15 2%1%~1,700 users$6.00/mo · Ministral 3 (3B)NoCompare →

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 252 makers' products on Claude that show this choice.

Markets that build with it most

Product Hunt markets where Claude is in far more of the stacks we know than across every market (4%).

When to use Claude, and when not

Pick Claude if

  • You want the strongest general models and the widest ecosystem of examples and integrations. LLM API →

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.
  • The agent must handle pages it has never seen, given only a goal: Browser Use.
  • You know most of the steps and want the model only for the parts that vary: Stagehand.
From each decision's guide, written from what makers' products chose and why.

The Claude API is Anthropic's developer interface to its Claude models. You send text, images and PDFs and get text back, so you can add chat, document analysis, coding help or agents that call your own tools to a product. It's a separate account and bill from the Claude chat app.

More about Claude

The core is the Messages API: you send the conversation so far, a system prompt and optional tool definitions, and Claude replies with text or with tool calls that your code runs before sending the results back. The API keeps no conversation state between calls; you resend the history each time. Keys belong to workspaces inside an organization. Official SDKs cover Python, TypeScript (Node.js, Deno, Bun and browsers), C#, Go, Java, PHP and Ruby, plus an ant CLI.

What matters for a small team: prompt caching for long repeated context, structured outputs, extended or adaptive thinking, citations and PDF input, and the Message Batches API for bulk jobs. On top of that, the Claude Agent SDK runs the agent loop in your own process, and Managed Agents runs it on Anthropic's infrastructure. Besides Anthropic's own API, the models are available on Amazon Bedrock, Google Cloud and Microsoft Foundry.

Limits: the models are closed and run only on Anthropic's or those cloud partners' infrastructure. On Anthropic's own API, inference can be pinned to the US, but there's no EU option yet: workspace data is stored only in the US.

How Claude itself is built

4 tools, from its own code, website and Product Hunt page.

Claude pros and cons

What makers like most: It is strong at writing code and powers many code generation and coding agent products. Their most common complaint: Outages are frequent, with uptime below three nines across the API and apps.

Pros

  • It is strong at writing code and powers many code generation and coding agent products. PHPH 2PH 3PH 4
  • It stays coherent through long, multi-step reasoning and agent workflows. PHPH 2PH 3PH 4
  • Its writing sounds natural and matches a user's tone rather than reading as AI-generated. PHPH 2PH 3PH 4
  • Makers trust its instruction-following and safety on untrusted content. PHPH 2PH 3
Product Hunt review tags
AI assistant108
code generation70
contextual understanding35
reasoning capabilities32
data analysis22
nuanced responses19

Cons and watch-outs

  • Outages are frequent, with uptime below three nines across the API and apps. HNHN 2HN 3HN 4
  • API pricing is a large multiple of subscription pricing, making heavy agent use expensive. HNHN 2HN 3
  • Postmortems confirmed periods of degraded output, including a lowered default reasoning effort in Claude Code. HN
  • Watermarking applied to all output and hidden request marking in Claude Code upset developers. HNHN 2
Product Hunt review tags
message limits10
typography issues10
contextual understanding2
conversation search2
limited image output2

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 1,049 reviews on Product Hunt ↗

What Hacker News says about Claude

On Hacker News, 28% of comments about Claude recommend it and 20% criticize it: net praise +8%, 11th best liked of 12 tools HN discusses for LLM API. Commenters chose it 2.9× as often per month in 2026 as in 2025.

By year

YearComments choosing it, per monthNet praise
20237.8+33%
202428+4%
2025148+16%
2026 (8 mo)429+4%

In their words

  • “I still use Claude code (and codex and other big contenders) because they know what they are doing and innovate” HN, Aug 2026
  • “I use Claude Code over Codex, OpenCode, Amp, etc primarily because of the UX” HN, Jul 2026
  • “I tried Claude Design, epic failure. Context windows exploding due to huge html files inlining images.” HN, Aug 2026

Hacker News comments January 2023 to August 2026 that name Claude in a sentence like "I use" or "we moved to", Claude read a sample of 100 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

Claude's status page posted 36+ incidents in the last 90 days, 17 major.

Incidents on its status page

36+ in the last 90 days, 17 major · 36+ in the last yearFrom its own status page, 2026-10-19. Vendors decide what they post; one page can cover several products.

Who switches

More projects move to Claude: 253 pull requests in, 223 out; the most come from OpenAI API and leave for Gemini API.

Moving to ClaudeMoving away
Claude
OpenAI API → Claude127 PRs
Gemini API → Claude108+ PRs
Groq → Claude10 PRs
DeepSeek → Claude8 PRs
Claude → Gemini API104+ PRs
Claude → OpenAI API88 PRs
Claude → DeepSeek16 PRs
Claude → Groq15 PRs

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

252 makers' products, each linked to the source that shows it, and 345 open-source projects that declare it in their code. The best known on Product Hunt: Writesonic (9,263 followers), Sider (3,883 followers), Chronicle (3,751 followers), Thesys (3,621 followers), Scarlett (3,290 followers). 7 of the makers' products are gone now (domain lapsed, up for sale or taken down); they chose Claude while live.

The maker says so 189Subprocessor list 72Job posting 1Declared in code 348How evidence is collected →
giselle
giselleGiselle is an open-source tool for building and running AI workflows in a visual node ed…

“Claude powers the intelligence behind Giselle's AI workflows. We leverage the full Claude family — Haiku for fast, cost-effective tasks on our free tier, Sonnet for balanced everyday workflows, and Opus for the most demanding reasoning challenges. Extended Thinking lets our workflows reason through multi-step problems, while multimodal capabilities enable understanding PDFs and images. The API's reliability and Claude's unique ability to follow complex instructions make it perfect for orchestrating sophisticated AI workflows. Thank you for building AI that truly thinks!”

LLM APIMaker says so +1 · source ↗
Slashy
SlashyAI email client that triages the inbox and drafts replies in your voice, connected to ca…

“We chose Claude because it is strong at understanding long, messy context and producing thoughtful, natural writing. That makes it especially useful for email workflows that depend on full threads, meeting notes, and CRM history.”

LLM APIMaker says so +1 · source ↗
Zed
ZedA code editor written in Rust with multiplayer collaboration and built-in AI features li…

“We're piloting Anthropic's new Fast Edit mode for Claude 3.5 Sonnet with a small set of Zed users.”

LLM APIMaker says so +1 · source ↗
Cekura
CekuraAutomated QA for Voice AI and Chat AI agents

“We use Claude models for parts of automated scenario generation, evaluation and building some of our pre-defined metrics”

LLM APIMaker says so +1 · source ↗
Human Behavior
Human BehaviorHuman Behavior is a product analytics tool whose SDK records events, errors and session…

“Claude powers our agents, including the coding agent that opens PRs”

LLM APIMaker says so +1 · source ↗
Skippr AI
Skippr AIThe live AI employee inside your product, serving every user

“One of our LLM providers, using multiple for different tasks, along with our own agent skills”

LLM APIMaker says so +1 · source ↗
Youkti
YouktiFinds who's ready to buy, then tells you what to do next

“Orchestrator synthesis, email scoring, coaching tips, meeting prep, weekly summaries”

LLM APIMaker says so +1 · source ↗
THEO Growth
THEO GrowthPositioning Intelligence for brand strategists

“Claude's advanced language understanding capabilities have been instrumental in shaping THEO's context-aware AI interactions and megaprompts in chains.”

LLM APIMaker says so +1 · source ↗
AI Emaily
AI EmailyYour AI inbox that writes like you + replies on autopilot

“Claude writes the replies that actually sound like our users. Best-in-class at tone, instruction-following, and staying safe on untrusted email content. It's why "drafts in your voice" works.”

LLM APIMaker says so +1 · source ↗
onlook
onlookOpen-source visual editor for React apps: designers edit the UI and the changes are writ…

“• Best at following nuanced design/editing instructions; fewer retries when transforming real React/Tailwind code. • High context windows make full-repo understanding practical for Onlook’s AI edits. • Reliable tool use and harmlessness out of the box reduces guardrail code we’d otherwise write. • Net: higher quality code changes without needing large amounts of prompt engineering.”

LLM APIMaker says so · source ↗
MindPal
MindPalMindPal is a no-code platform for turning a person's expertise into AI agents and multi-…

“You can select Claude from Anthropic, arguably the smartest models, to power the AI agents you build on MindPal!”

LLM APIMaker says so · source ↗
Lovable
LovableAI app builder that generates full-stack web apps from a chat, with backend features pro…

“One of the main technologies we use for powering Lovable, even more performant with latest models.”

LLM APIMaker says so · source ↗
FirstQuadrant
FirstQuadrantMaximize B2B sales with human-centered AI

“Claude powers some of the most nuanced and context-aware conversations in FirstQuadrant. A foundational model that we deeply rely on.”

LLM APIMaker says so · source ↗
RunLLM
RunLLMAI that doesn’t just respond—it resolves

“Claude 3 Opus handles longer context and nuanced conversation better than most. Great for logs, long-form reasoning, and fallback flows. Best long-context memory and thoughtful responses.”

LLM APIMaker says so · source ↗
Chronicle
ChronicleAI presentation tool that generates slides from a prompt or notes, with an editor and ex…

“Our go-to partner for shaping the storytelling core of our presentations. Its ability to contextualize complex ideas into concise, impactful first drafts elevates our narrative quality.”

LLM APIMaker says so · source ↗
Composio
ComposioGives AI agents access to 1,000+ third-party tools, handling OAuth, permissions and exec…

“The LLM engine 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 ↗
Deepgram
DeepgramSpeech AI API for speech-to-text, text-to-speech and voice agent building, plus audio in…

“Anthropic's models' nuanced understanding and reliable outputs have been essential in creating a more intelligent and responsive experience for our users. We're excited to be building with their technology.”

LLM APIMaker says so · source ↗
Melies
MeliesMelies is an AI filmmaking studio for writing a script and generating the images, video,…

“Melies uses different Claude 3.5 Sonnet primarly in the application for screenwriting and transforming scripts into movies, as well as other lighter models such as Haiku.”

LLM APIMaker says so · source ↗
reflex
reflexOpen-source Python framework for building full-stack web apps, frontend and backend, in…

“Claude’s long context and solid reasoning made it perfect for generating full-stack Python apps.”

LLM APIMaker says so · source ↗
Thesys
ThesysC1 is an API that makes LLM responses come back as interactive UI components such as cha…

“Integrated to leverage state-of-the-art models for language understanding and generation.”

LLM APIMaker says so · source ↗
Anything
AnythingAI agent that builds mobile apps, websites and tools from a description, with database,…

“Sonnet powers much of the code gen in Anything. It's also a built in integration in Anything that just works in your app when you say "add AI"”

LLM APIMaker says so · source ↗
Databox
DataboxAgentic analytics platform for you and your agents.

“Routines run without anyone watching. That means the reasoning has to hold up on its own, no follow-up question to catch a mistake, no chance to rephrase and try again. Claude does the actual analysis behind every run: reading the data, working out what changed and why, and writing a result that has to be right the first time, because for most runs, no one checks it before it lands in someone's inbox.”

LLM APIMaker says so · source ↗
Agentplace.io
Agentplace.ioAI agents that serve your customers

“A family of foundational AI models Claude Sonnet and Opus help us power reliable, high-quality reasoning across Agentplace”

LLM APIMaker says so · source ↗
Hello Inbox
Hello InboxMaximize inbox placement for email marketing campaigns

“A RAG system is only as good as the model sitting on top of it. You can build perfect retrieval — clean embeddings, well-chunked documents, low-latency vector search — and still end up with an assistant that gives technically accurate but practically useless answers. That's the problem Anthropic's Claude solves for Hello Inbox.”

LLM APIMaker says so · source ↗
LaunchSafe
LaunchSafeAutonomous Pentesting for Modern Applications

“The brain behind our security agents. Claude Opus reasons through code like a senior pentester — finding exploit chains, not just pattern matching. Massive context window + reliable API. Nothing else comes close.”

LLM APIMaker says so · source ↗
Nautis
NautisThe AI-native Operating System for founders.

“Added depth, reasoning, and reliability to AI-driven experiences on the platform. A key part of helping founders make smarter and faster operational decisions.”

LLM APIMaker says so · source ↗
Officely AI
Officely AIAny Process to AI with All LLM Models

“We use Claude as an endpoint in our team builder flow; you can combine this model with all available models.”

LLM APIMaker says so · source ↗
Spine
SpineBuilding autonomous agents for everyday work.

“At Spine Research, users can choose between all the major LLMs to generate deep, structured research reports. Anthropic’s models have consistently delivered the best results for synthesizing large volumes of information into well-written, insightful narratives—making them the default choice on our platform.”

LLM APIMaker says so · source ↗
n8nChat
n8nChatn8nChat is a Chrome and Firefox extension that builds, edits and debugs n8n workflows fr…

“Anthropic's Claude models deliver exceptional reasoning capabilities for complex workflow generation while maintaining strong guardrails. What makes them better is their ability to understand nuanced technical instructions with fewer hallucinations and their long context windows (up to 200K tokens), which allows the extension to generate more complex, multi-node workflows in a single interaction.”

LLM APIMaker says so · source ↗
Agentcard
AgentcardIssues virtual debit cards to AI agents such as Claude or OpenClaw so they can pay for t…

“Claude is the AI model behind our smartest agent integrations. Anthropic's focus on safety aligns perfectly with how we think about giving agents financial capabilities — powerful but controlled.”

LLM APIMaker says so · source ↗
Bubble
BubbleVisual no-code platform for building and hosting full-stack web and native mobile apps,…

“Claude is one of our preferred AI models at Bubble. We use their suite of tools to support prototyping and early-stage thinking. Plus, early versions (still not public) AI-generated mobile apps use Claude.”

LLM APIMaker says so · source ↗
Prisma
PrismaTypeScript ORM with a schema file and generated client; also offers hosted Prisma Postgr…

“We used Anthropic to deliver a powerful AI assistant in our Prisma Optimize product, which allows developers to more easily improve their database performance.”

LLM APIMaker says so · source ↗
Rezonant
RezonantProduct workspace for teams that build with coding agents: turns ideas and team context…

“Our agent and coding agent tasks kicked off from Rezonant use Anthropic's models!”

LLM APIMaker says so · source ↗
Nerve
NerveGone · site taken down on its host, Oct 2026AI Chief of Staff that does your actual work

“We use a combination of OpenAI, Claude, and Gemini models under the hood”

LLM APIMaker says so · source ↗

Open source: a project that declares Claude as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

150 of the 225 open-source products built with Claude that were worked on in the last 180 days keep instruction files for coding agents — 67%, against 53% of all the projects we read. AGENTS.md is in 121, CLAUDE.md in 95.

1,027words in the median file
uvthe package manager most named, in 37 of 137 files
68%say how to test a change
Named more in these files than in other projects' — in how many of the 137:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to Claude

All alternatives by situation →

Further reading

Questions makers ask about Claude

Is Claude good for production?

252 makers' products we track run on it, and 7 of them have since gone (the product, not necessarily because of Claude). Its own status page posted 36+ incidents in the last 90 days, 17 of them major; vendors decide what they post there, so this doesn't compare across tools. On GitHub, 253 public pull requests moved projects to Claude from tools we list, and 223 moved them away. The watch-out makers raise most: Outages are frequent, with uptime below three nines across the API and apps.

What is Claude used for?

Anthropic's Claude models via API, strong at coding, long documents and tool use. Makers' products we track use it for LLM API (252).

What are the pros and cons of Claude?

Pros makers name: It is strong at writing code and powers many code generation and coding agent products. It stays coherent through long, multi-step reasoning and agent workflows. Its writing sounds natural and matches a user's tone rather than reading as AI-generated. Cons: Outages are frequent, with uptime below three nines across the API and apps. API pricing is a large multiple of subscription pricing, making heavy agent use expensive. Postmortems confirmed periods of degraded output, including a lowered default reasoning effort in Claude Code.

What are the alternatives to Claude?

For LLM API, the other options makers' products we track chose most are OpenAI API (736), Gemini API (99), Groq (39), Azure OpenAI (22), Mistral AI (15). Each alternative, with the situation it fits, is on the Claude alternatives page.

Is Claude still popular with new products?

Less than before: among the 256 makers' products launched in 2026 that made the LLM API choice, 21% chose Claude, against 24% of the 316 launched in 2024 or earlier.

How much does Claude cost per month?

At 10,000 users, Claude costs $10 a month on the cheapest plan that fits (Claude Haiku 5.5), from its pricing page.

Do developers switch to or away from Claude?

On GitHub, 253 public pull requests moved projects to Claude from tools we list, most from OpenAI API (127), Gemini API (108), Groq (10); 223 moved them away, most to Gemini API (104), OpenAI API (88), DeepSeek (16).

When should you use Claude?

You want the strongest general models and the widest ecosystem of examples and integrations (LLM API). 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 Anthropic train on data I send through the API?

No, not by default. Inputs and outputs from commercial products, including the API, aren't used for training unless you report feedback or otherwise opt in. source ↗

How long are API prompts and responses kept?

Anthropic deletes API inputs and outputs from its backend within 30 days. The exceptions are data in features you keep yourself (such as the Files API), a zero-data-retention agreement, usage-policy enforcement, and legal requirements. source ↗

Can I control where my data is processed and stored?

Partly. You can set inference_geo per request or as a workspace default to keep inference on US infrastructure (Claude 4.6 and later models), but the workspace storage location can't be changed after creation, and "us" is currently the only option. source ↗

Can I send PHI and sign a BAA?

Yes. Anthropic offers a BAA for HIPAA-ready services, including the first-party API. Your organization's Primary Owner signs it and then asks sales or your Anthropic contact to enable it, and it covers only that one organization. source ↗

Can I call Claude with the OpenAI SDK?

Yes, through a compatibility layer, but some fields are silently ignored. For example, strict tool schemas aren't enforced, audio input isn't supported, and thinking output isn't returned. For PDFs, citations, prompt caching and full thinking, Anthropic points you to the native API. source ↗

How do rate limits and spend caps work?

Limits are set per organization and depend on a usage tier that rises automatically with usage history. Each tier below Custom has a monthly spend cap; when you hit it, requests return 429 until the next month unless you ask for a higher limit. source ↗

Is there a batch mode for large offline jobs?

Yes. The Message Batches API takes up to 100,000 requests or 256 MB per batch, usually finishes within an hour, and cuts costs by 50%. Batches expire after 24 hours, and results stay downloadable for 29 days. source ↗

Which languages have an official SDK?

Python, TypeScript, C#, Go, Java, PHP and Ruby, plus the ant command-line tool. source ↗

Is Claude free?

No permanent free tier; paid use starts at Pay per token. source ↗

Is Claude open source or self-hostable?

Not open source, and hosted only.

Can AI coding agents work with Claude?

It serves an llms.txt docs index; Lovable, Replit set it up natively.

Who uses Claude?

252 makers' products we track, each with a source, and 345 open-source projects declare it in their code. The best known of them on Product Hunt: Writesonic (9,263 followers), Sider (3,883 followers), Chronicle (3,751 followers), Thesys (3,621 followers), Scarlett (3,290 followers). source ↗