Hacker ApprovedDepartments

Anthropic API

Ranked 4 of 10 LLM APIs by recommenders

Recommended for straightforward pay-per-use access to Claude models with clear, stable pricing and no client lock-in. Common caveat: high token costs and uptime or account-suspension worries.

Recommended for straightforward pay-per-use access to Claude models with clear, stable pricing and no client lock-in. Common caveat: high token costs and uptime or account-suspension worries.

184 people gave an opinion

recommend it
58
criticize it
126
approval share
32%
Each figure is 2 people. RecommendsCriticizes

Recommended in 12 of 13 months

  1. November 2025: recommended
  2. December 2025: recommended
  3. January 2026: recommended
  4. February 2026: recommended
  5. March 2026: recommended
  6. April 2026: recommended
  7. May 2026: recommended
  8. June 2026: recommended
  9. July 2026: recommended
  10. August 2026: recommended
  11. September 2026: recommended
  12. October 2026: recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 58 people recommend itNeeds 10 or more, met.
  • 0.4 recommenders for every criticNeeds 2 to 1 or better, not met.
  • Recommended in 12 of 13 monthsNeeds 4 or more, met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Straightforward and easy to use

    “$200 free credits from Anthropic are stupid simple to use”

    Comment from 13 Oct 2026 in “Gemini 4 Argon”

    “The API is there. It's straightforward and easy to use.”

    Comment from 4 Apr 2026 in “Anthropic no longer allowing Claude Code subscriptions to be used with OpenClaw”
  • Flexible access without client lock-in

    “The API gives you the same flexibility without the risk of getting your account suspended.”

    Comment from 6 Feb 2026 in “Claude Opus 4.6 extra usage promo”

    “They have a separate product intended for use with general tools: Their API.”

    Comment from 19 Mar 2026 in “Anthropic takes legal action against OpenCode”

    “just use the API which doesn't lock you into any client”

    Comment from 9 Jan 2026 in “Anthropic bans use of API in OpenCode CLI tool”
  • Stable costs and clear pricing

    “their API has a model selection anyone can understand and pricing that rarely changes”

    Comment from 30 May 2026 in “Anthropic surpasses OpenAI to become most valuable AI startup”

    “If you want stable costs, the API plan is right there.”

    Comment from 6 Jul 2026 in “Anthropic's Method to Losing Goodwill in a Few Easy Steps”

    “The API offers that. Pay X per month, get Y tokens.”

    Comment from 4 Apr 2026 in “Anthropic no longer allowing Claude Code subscriptions to be used with OpenClaw”
  • Direct developer API access

    “direct-to-dev type API access oAI and Anthropic have pioneered”

    Comment from 24 Nov 2025 in “Nano Banana Pro”

    “If you don't want to use CC, just use the API”

    Comment from 9 Jan 2026 in “Anthropic bans use of API in OpenCode CLI tool”

What people warn about

Each mark is one comment

  • Token costs high and unpredictable

    “It's pretty easy to hit a couple hundred dollars a day filling up Opus's context window with files.”

    Comment from 16 Dec 2025 in “AI will make formal verification go mainstream”

    “Anthropic is also so insanely expensive for everything”

    Comment from 3 Sep 2026 in “Gemini 3.8 Flash and 3.8 Flash Cyber”

    “it will just start charging you API prices for the tokens you are generating without even a single warning”

    Comment from 7 Oct 2026 in “Claude Haiku 5.5”
  • Data use and training concerns

    “Anthropic has made their arguments (that I disagree with) that model outputs, no matter how much user context was fed, do not fall under their definition of "user data".”

    Comment from 26 Oct 2026 in “OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?”

    “when they say they store your data for 30 days and review it for "issues", it makes your "spider sense" tingle”

    Comment from 10 Jun 2026 in “AWS Bedrock to require sharing data with Anthropic for Mythos and future models”

    “The idea OpenAI or Anthropic won't train on your data—even with an enterprise contract—is a fantasy at best”

    Comment from 8 Sep 2026 in “On the Navier–Stokes Millennium Prize Problem”
  • Accounts and keys suspended without warning

    “Within seconds I got an email from Anthropic and they have already disabled my keys.”

    Comment from 13 Dec 2025 in “Home Depot GitHub token exposed for a year, granted access to internal systems”

    “Anthropic is unsurprisingly leading the race to the bottom of the barrel by requiring moderator reviews for API customers.”

    Comment from 19 Oct 2026 in “MiniMax M3.1 Flash”
  • Outages and weak uptime

    “it's quite telling that when adding API keys for Anthropic, it presents a note inbetween reading "Experiencing Issues? Check Anthropic status"”

    Comment from 11 Mar 2026 in “Ask HN: Is Claude Down Again?”

    “how are they a near trillion dollar company with models so good they are treated as weapons yet have almost no 9's of uptime”

    Comment from 6 Jul 2026 in “Anthropic's Method to Losing Goodwill in a Few Easy Steps”

    “Do you want your company's sales and customer service to shut down every time OpenAI or Anthropic goes down?”

    Comment from 4 Sep 2026 in “Corporate America is getting hooked on open-source AI”

Other LLM APIs people recommend

The four most recommended other LLM APIs, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

Anthropic API compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
Mistral31424556%136 mo9 owners—
DeepSeek API1715675%111 mo9 ownersApproved
OpenAI API16628637%139 mo7 owners—
Anthropic APIThis page5812632%12——
System One Models by TypeSafe37784%2——
See all 10 LLM APIs, ranked

What people said

40 of the 191 comments that mention it, newest first. Each links to the original comment.

“Anthropic has made their arguments (that I disagree with) that model outputs, no matter how much user context was fed, do not fall under their definition of "user data".”

CriticizesComment from 26 Oct 2026 in “OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?”

“Anthropic is unsurprisingly leading the race to the bottom of the barrel by requiring moderator reviews for API customers.”

CriticizesComment from 19 Oct 2026 in “MiniMax M3.1 Flash”

“$200 free credits from Anthropic are stupid simple to use”

RecommendsComment from 13 Oct 2026 in “Gemini 4 Argon”

“it will just start charging you API prices for the tokens you are generating without even a single warning”

CriticizesComment from 7 Oct 2026 in “Claude Haiku 5.5”

“It's pretty reliable, though sometimes just because of where the doorbell camera is it can't clearly see the bins.”

RecommendsComment from 4 Oct 2026 in “Surely you have ultra-wideband radios on your bins too?”

“There is no reason to pay API prices for Anthropic and OpenAI if they don't cut them down 100x at least.”

CriticizesComment from 27 Sep 2026 on Hacker News

“I also have openai and anthropic direct API billing set up for hosted and client projects”

RecommendsComment from 24 Sep 2026 in “Best LLM for every budget, updated daily”

“The idea OpenAI or Anthropic won't train on your data—even with an enterprise contract—is a fantasy at best”

CriticizesComment from 8 Sep 2026 in “On the Navier–Stokes Millennium Prize Problem”

“Do you want your company's sales and customer service to shut down every time OpenAI or Anthropic goes down?”

CriticizesComment from 4 Sep 2026 in “Corporate America is getting hooked on open-source AI”

“Anthropic is also so insanely expensive for everything”

MixedComment from 3 Sep 2026 in “Gemini 3.8 Flash and 3.8 Flash Cyber”

“And you're claiming Anthropic and OpenAI are not doing the same thing?”

MixedComment from 15 Aug 2026 in “Qwen3.8-27B”

“Experimenting can be pricey but early on I spent my own money thinking "if I can get a handle on how to do this I'll get a 100x return on my money" and it was a good bet.”

RecommendsComment from 14 Jul 2026 in “Punch Yourself in the Face with Reality”

“If you want stable costs, the API plan is right there.”

RecommendsComment from 6 Jul 2026 in “Anthropic's Method to Losing Goodwill in a Few Easy Steps”

“how are they a near trillion dollar company with models so good they are treated as weapons yet have almost no 9's of uptime”

CriticizesComment from 6 Jul 2026 in “Anthropic's Method to Losing Goodwill in a Few Easy Steps”

“when they say they store your data for 30 days and review it for "issues", it makes your "spider sense" tingle”

CriticizesComment from 10 Jun 2026 in “AWS Bedrock to require sharing data with Anthropic for Mythos and future models”

“if a customer is actually using their api to the limits they set, they lose money”

MixedComment from 2 Jun 2026 in “Can the stockmarket swallow Anthropic, SpaceX and OpenAI?”

“their API has a model selection anyone can understand and pricing that rarely changes”

RecommendsComment from 30 May 2026 in “Anthropic surpasses OpenAI to become most valuable AI startup”

“We find OpenAI, Anthropic and Fireworks (which we use a lot) all have higher cache hit rates.”

RecommendsComment from 19 May 2026 in “Gemini 3.5: frontier intelligence with action”

“Anthropic has a massive API platform with things like Sessions, Files, and Agents”

RecommendsComment from 11 May 2026 in “Gemini API File Search is now multimodal”

“due to the reliability of Anthropic’s API, less of a friction despite slower response times”

RecommendsComment from 2 May 2026 in “DeepSeek V4–almost on the frontier, a fraction of the price”

“my work handed me a bottomless anthropic API key to use for claude code”

MixedComment from 12 Apr 2026 in “Sam Altman's response to Molotov cocktail incident”

“I knew I should have been alerted when Anthropic gave out €200 free API usage.”

MixedComment from 6 Apr 2026 in “Claude Code is unusable for complex engineering tasks with the Feb updates”

“The API offers that. Pay X per month, get Y tokens.”

RecommendsComment from 4 Apr 2026 in “Anthropic no longer allowing Claude Code subscriptions to be used with OpenClaw”

“The API is there. It's straightforward and easy to use.”

RecommendsComment from 4 Apr 2026 in “Anthropic no longer allowing Claude Code subscriptions to be used with OpenClaw”

“Publishing this list proactively rather than only on request is a positive signal”

RecommendsComment from 27 Mar 2026 in “Anthropic Subprocessor Changes”

“I think only Anthropic's API would give enough control to do this today”

MixedComment from 23 Mar 2026 in “Apply video compression on KV cache to 10,000x less error at Q4 quant”

“They have a separate product intended for use with general tools: Their API.”

RecommendsComment from 19 Mar 2026 in “Anthropic takes legal action against OpenCode”

“it's quite telling that when adding API keys for Anthropic, it presents a note inbetween reading "Experiencing Issues? Check Anthropic status"”

CriticizesComment from 11 Mar 2026 in “Ask HN: Is Claude Down Again?”

“If it's the exact shape of Anthropic's API, the difference is surely minor”

MixedComment from 7 Mar 2026 in “Claude AI Helped Bomb Iran. But How Exactly?”

“I can't use any of my cards (personal or corporate) for OpenAI or Anthropic.”

MixedComment from 19 Feb 2026 in “Anthropic officially bans using subscription auth for third party use”

“I spent about 500 dollars and 16 hours of conversation to get an MVP static marketplace”

RecommendsComment from 16 Feb 2026 in “"token anxiety"; or, a slot machine by any other name”

“The API gives you the same flexibility without the risk of getting your account suspended.”

RecommendsComment from 6 Feb 2026 in “Claude Opus 4.6 extra usage promo”

“I’ve grown very accustomed to the model and would rather not switch until I find a real need to.”

RecommendsComment from 15 Jan 2026 in “Anthropic is making a huge mistake”

“The price difference between the regular API and the Oauth API is too large.”

MixedComment from 12 Jan 2026 in “Anthropic Made a Big Mistake”

“You can use their API on a pay-per-use basis, or (as I interpreted the agreement) you can prepay as a subscription”

MixedComment from 12 Jan 2026 in “Anthropic Made a Big Mistake”

“If you don't want to use CC, just use the API”

RecommendsComment from 9 Jan 2026 in “Anthropic bans use of API in OpenCode CLI tool”

“just use the API which doesn't lock you into any client”

RecommendsComment from 9 Jan 2026 in “Anthropic bans use of API in OpenCode CLI tool”

“It's pretty easy to hit a couple hundred dollars a day filling up Opus's context window with files.”

MixedComment from 16 Dec 2025 in “AI will make formal verification go mainstream”

“Within seconds I got an email from Anthropic and they have already disabled my keys.”

RecommendsComment from 13 Dec 2025 in “Home Depot GitHub token exposed for a year, granted access to internal systems”

“direct-to-dev type API access oAI and Anthropic have pioneered”

RecommendsComment from 24 Nov 2025 in “Nano Banana Pro”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.