aifree.dev

Free LLM rate-limit calculator

Enter the requests per day and request size you need: see which free LLM tiers cover it alone, which combination of up to three does, and the headroom left.

Published per-minute, per-day and per-month request limits and tokens per minute or per day only, from the same catalog as the free LLM API picker; see how we verify.

Prefilled from Groq Free Tier (openai/gpt-oss-120b): the requests per day its published limits allow at ~800 tokens. Change the numbers to your app’s peak day.

Reset

Your result

250 requests/day at ~800 tokens: 18 free tiers cover it alone

  • 250 req/day
  • ~800 tokens

Covers it alone (18)

Most headroom first. "Cap / day" is what the published limits allow at your request size; the bound that produced it is named.

OfferModelCap / dayLimited byHeadroomSpare / dayCardStatusNotes
AI21 Labs Free Trial logoAI21 Labs Free TrialJamba LargeOther288,000requests per minute, sustained100%287,750No cardVerified · Oct 12, 2026, how we verifyFoundation model limits: 10 RPS, 200 RPM; same for trial keys
Alibaba Cloud Model Studio Free Token Quota logoAlibaba Cloud Model Studio Free Token Quotaqwen-plusQwen864,000requests per minute, sustained100%863,750No cardVerified · Nov 15, 2026, how we verifySingapore region account-level limit; other regions differ
Cloudflare Workers AI Free Tier logoCloudflare Workers AI Free Tier@cf/meta/llama-3.3-70b-instruct-fp8-fastLlama432,000requests per minute, sustained100%431,750No cardVerified · Nov 15, 2026, how we verifyText Generation: 300 requests per minute; counts against 10,000 free Neurons/day
Mixedbread Free Starter Credits logoMixedbread Free Starter CreditsToast 1Other144,000requests per minute, sustained100%143,750No cardVerified · Nov 15, 2026, how we verifyStarter tier: 100 queries/min, 6,000 uploads/min
OVHcloud AI Endpoints Free Tier logoOVHcloud AI Endpoints Free TierQwen3.8-27BQwen576,000requests per minute, sustained100%575,750CardVerified · Oct 12, 2026, how we verify400 req/min per project and per model when authenticated; 2 req/min anonymous
Sarvam AI Free API Credits logoSarvam AI Free API Creditssarvam-105bOther57,600requests per minute, sustained100%57,350No cardVerified · Nov 15, 2026, how we verifyStarter tier chat limit for this model (other chat models 60 req/min)
Scaleway Generative APIs Free Tier logoScaleway Generative APIs Free Tierglm-5.2Other360,000tokens per minute at your request size100%359,750No cardVerified · Nov 15, 2026, how we verifySupported model; per-model limits in Organization quotas, not on docs
Token Harbor Free Allowance logoToken Harbor Free AllowanceDeepSeek V4.1 FlashDeepSeek86,400requests per minute, sustained100%86,150No cardVerified · Nov 15, 2026, how we verifyFree plan allowance resets on a rolling 7-day period; no limits published
Token Harbor Free Allowance logoToken Harbor Free AllowanceMiMo V2.6 FlashOther86,400requests per minute, sustained100%86,150No cardVerified · Nov 15, 2026, how we verifyFree allowance resets on a rolling 7-day period; limits unpublished
Upstage AI Initiative Free Access logoUpstage AI Initiative Free Accesssolar-pro4Other144,000requests per minute, sustained100%143,750No cardVerified · Nov 6, 2026, how we verifyDefault limits from the chat quickstart table; tier-assigned
AMD Radeon Cloud Free APIs logoAMD Radeon Cloud Free APIsDeepSeek-V4-FlashDeepSeek43,200requests per minute, sustained99%42,950No cardVerified · Nov 6, 2026, how we verifyTypical per-key 30 RPM and 8 concurrent; spend cap per account
Cohere Free Trial API logoCohere Free Trial APIcommand-a-plus-05-2026Other28,800requests per minute, sustained99%28,550No cardVerified · Nov 15, 2026, how we verifyTrial chat limit 20 req/min; trial keys capped at 1,000 API calls a month
NaraRouter Free Tier logoNaraRouter Free TierAgnes 2.5 FlashOther21,600requests per minute, sustained99%21,350No cardVerified · Nov 15, 2026, how we verifyFree plan: 15 req/min, 7M tokens per day shared
Agnes AI Free API logoAgnes AI Free APIagnes-2.5-flashOther14,400requests per minute, sustained98%14,150No cardVerified · Nov 6, 2026, how we verifyDefault keys: text models effective 10 RPM; free keys and Token Plan keys use separate pools
NVIDIA NIM Free Inference Endpoints logoNVIDIA NIM Free Inference Endpointsdeepseek-v4.1-flashDeepSeek10,000requests per day98%9,750No cardVerified · Nov 6, 2026, how we verifyFree inference endpoint; limits not published
Cerebras Inference Free Trial logoCerebras Inference Free Trialgpt-oss-120bGPT1,000,000 tokens/day1,250tokens per day at your request size80%1,000CardVerified · Oct 12, 2026, how we verifyFree Trial: 5 RPM, 30K uncached TPM, 1M TPD; 65k context on free vs 131k paid
Infron Free AI Models logoInfron Free AI Modelsdeepseek/deepseek-v4.1-flash:freeDeepSeek1,000requests per day75%750No cardVerified · Oct 12, 2026, how we verifyStandard free model; 1,000 requests/day per account shared across free models; requires a $5+ balance
Groq Free Tier logoGroq Free Tieropenai/gpt-oss-120bGPT200,000 tokens/day250tokens per day at your request size0%0No cardVerified · Oct 12, 2026, how we verifyFree Plan Limits tab; TPD 200K

Combine 2 tiers

Spread across 2 providers the published caps add up to 400 requests a day, 38% headroom. One key per provider; nothing from the same vendor is counted twice.

OfferModelCap / dayLimited byHeadroomSpare / dayCardStatusNotes
Requesty Free Models logoRequesty Free Modelsnvidia/nemotron-3-ultra-550b-a55bOther200requests per day-25%-50 (short of 250)No cardVerified · Nov 15, 2026, how we verifyFree plan: 200 requests/day across all models
Routeway Free Models logoRouteway Free ModelsDeepSeek V4 Flash (Free)DeepSeek200requests per day-25%-50 (short of 250)No cardVerified · Nov 6, 2026, how we verifyFree tier 200 req/day (cannot be increased); 20 RPM per the FAQ

Not enough alone (5)

Published, but below your need on their own. Largest first.

OfferModelCap / dayLimited byHeadroomSpare / dayCardStatusNotes
Requesty Free Models logoRequesty Free Modelsnvidia/nemotron-3-ultra-550b-a55bOther200requests per day-25%-50 (short of 250)No cardVerified · Nov 15, 2026, how we verifyFree plan: 200 requests/day across all models
Routeway Free Models logoRouteway Free ModelsDeepSeek V4 Flash (Free)DeepSeek200requests per day-25%-50 (short of 250)No cardVerified · Nov 6, 2026, how we verifyFree tier 200 req/day (cannot be increased); 20 RPM per the FAQ
LLM7.io Free Tier logoLLM7.io Free TierDeepSeek-V4-Flash-0731DeepSeek100,000 tokens/day125tokens per day at your request size-100%-125 (short of 250)No cardVerified · Nov 6, 2026, how we verifyFree token: 100,000 tokens per 24 hours, 60 req/min; limits shared across models
OpenRouter Free AI Models logoOpenRouter Free AI ModelsNVIDIA: Nemotron 3 Ultra (free)Other50requests per day-400%-200 (short of 250)No cardVerified · Nov 15, 2026, how we verifyAll :free variants: 20 RPM; 50 RPD without credits, 1,000 RPD after 10+ credits
OrcaRouter Free AI Models & API Credits logoOrcaRouter Free AI Models & API Creditsdeepseek/deepseek-v4-flash-freeDeepSeek50requests per day-400%-200 (short of 250)No cardListed · Sep 10, 2026, how we verifyLimits published only at GET /api/free-package/public

Limits not published (37)

The vendor publishes no requests-per-minute, requests-per-day or tokens-per-minute figure for the free tier, so these are listed, not scored. The offer page links the vendor page.

Which free APIs publish the highest limits? Highest free rate limits, ranked

Understand it

A few minutes of play-along, no sign-up.

Frequently asked questions

How is "requests per day" computed for a tier?
From the published limits only: the smallest of requests per day, requests per minute times 1,440 (the per-minute cap sustained all day, a ceiling rather than a promise), tokens per minute times 1,440 divided by your average request size, and, where the vendor publishes them, tokens per day divided by your average request size and requests per month divided by 30. The row says which bound limits you.
Why is a tier listed under "limits not published"?
Its vendor publishes no requests-per-minute, requests-per-day or tokens-per-minute figure for the free tier on a page we can cite, so there is nothing to compute from. aifree.dev never guesses a number; the offer page links the vendor page and notes.
How does the combination work?
Greedily: the largest tier that falls short goes first, then the next largest from a different provider, up to three providers, until the sum covers your need. Keys from one vendor are never combined because they usually share one quota. It is a spread of load, not a single key.
What limits are not covered?
Daily token caps and monthly call caps enter the arithmetic once they are recorded (shown under the model name), but some tiers still carry them only in the notes column, and monthly token caps or credit balances are not modelled. A tier with such a cap in its notes may be overstated; read its notes before relying on it.
Is the result the same for everyone?
Yes. The result is a pure function of the catalog and the two numbers in the URL, so a shared link shows the same answer until the next monthly re-check updates a limit.

Never miss new offers and news

New tools, credits, and AI news are added regularly. Pick how you want to hear about them.

Telegram channel

Join @aifree_dev and get new free AI offers and news right in your Telegram feed.

Browser notifications

Turn on push notifications and get an alert on this device whenever something new is posted. No account needed.

Email newsletter

A weekly digest of new, changed and expiring free AI offers. Double opt-in, one-click unsubscribe. See the latest issue.

Unsubscribe anytime. Privacy

Frequently asked questions

What is aifree.dev?

aifree.dev helps everyone access AI through a curated directory of free AI tools, API credits, free tiers, and startup programs for coding, image, voice, video, and students - verified regularly.

How are offers presented?

Each offer includes its access details, free models when available, and expiration information when provided. Limited-time deals stay visible so they are easy to compare.

Do education and startup programs need verification?

Yes. Providers usually ask students to verify their status with a school email, student ID, or a program like the GitHub Student Pack, and ask startups to verify company details such as age, funding, or website. Check each offer’s claim page for the exact requirements.

What kinds of free AI offers are listed?

Free tiers and free trials from AI providers, free API credits, startup and student programs, and free tools for coding, image generation, voice, and video.

How can I suggest a tool or report a broken link?

Use the submit form: paste the offer page URL and a short note. A person checks every submission before anything is listed. Broken links and changed terms go through the same form.

Know a good one?

Tell us about an AI tool worth knowing. Found a broken link? We want to hear that too.

Submit an offer