Guide

Free LLM API rate limits

Every free LLM API has rate limits. This page shows the free limits of each provider in the FreeLLMAPI catalog, in one table. It also tells you how to read RPM, RPD, TPM and TPD, and how to add free tiers together.

Free limits for every provider

The table comes from the live catalog. It has one row for each provider. Each value is the highest limit of any free model from that provider. One model can have a lower limit than the value in the row. A dash means that the provider does not publish that limit.

ProviderFree modelsMax req/minMax req/dayMax tokens/minTokens/month (one model)Strongest free model
ElectronHub84---$0.25/week shared recurring creditQwen3.8 Flash (ElectronHub)
qwen3.8-flash
Cloudflare Workers AI39---~5-10MQwen 3.8 27B (Cloudflare Workers AI)
@cf/qwen/qwen3.8-27b
Inferbase38---5,000 requests/month; 100 requests and $0.50 usage/day sharedDeepSeek V4 Flash (fp8) (Inferbase)
deepseek-v4-flash:fp8
AI Horde31---Ongoing volunteer queue; availability variesGemma 4 31B Heretic (AI Horde)
koboldcpp/gemma-4-31B-it-heretic
ACLIDE29---€20/month shared internal usage credits · no cardQwen3.8 Max (ACLIDE)
qwen/qwen3.8-max:free
Google AI Studio21151,000250,000~3MGemini 3.8 Flash
gemini-3.8-flash
Api.Airforce2011,000-free · 1,000 req/day · 1 req/mingpt-oss-20b (Api.Airforce)
gpt-oss-20b
NVIDIA NIM1940--free · 40 RPMGLM 5.3 Flash (NV)
z-ai/glm-5.3-flash
Cohere172033-~1-2MCommand A+ (05-2026)
command-a-plus-05-2026
DreamPrompting141005,000-free · 500K tokens/day · 5,000 req/dayGemini 3.1 Flash-Lite
google/gemini-3.1-flash-lite
Mistral122-500,000~50-100MMistral Code
mistral-code-latest
ModelScope11-200-Daily login: 200 credits + 50 for linked Alibaba Cloud; 24h expiry; shared; noncommercial experienceGLM-5.2 (ModelScope)
ZhipuAI/GLM-5.2
OVH AI Endpoints112--free · 2/min per IPQwen3.8 27B (OVH)
Qwen3.8-27B
Waterfall11---free · community rate limitnex-n2.5-pro (Waterfall)
nex-n2.5-pro-free
xKiro9---free · 500K tokens/day (1M with Telegram)SenseNova 6.8 Flash-Lite (xKiro)
sensenova/sensenova-6.8-flash-lite
Kilo Gateway8---free · 200/hr per IP (trial)Dots3 Note Preview (Kilo)
dots-studio/dots-3-note-preview:free
OpenRouter82050-~6MDots3 Note Preview (free)
dots-studio/dots-3-note-preview:free
Groq73014,40070,000~6MQwen3.8 27B (Groq)
qwen/qwen3.8-27b
Requesty7-200-free · 200 rpdLing 3.1 Flash (Requesty)
novita/ling-3.1-flash
Routeway75200-free · zero-priced routeMuse Glimmer 30B (Routeway free)
muse-glimmer-30b:free
Speka7---$1/month shared model-usage allowanceStep 5 Preview (Speka)
stepfun-ai/step-5-preview
APINex65--10M weighted tokens/day shared across APINex free routes; 4x token multiplier; 5 requests/minute/accountGLM 5.3 (APINex Free)
free/glm-5.3
Gizmo6---1,000 free-model requests/month · shared account quotaQwen3.8 27B (Gizmo)
qwen/qwen3.8-27b:free
SEA-LION610--free · 10 RPMQwen SEA-LION v4.5 27B (SEA-LION)
aisingapore/Qwen-SEA-LION-v4.5-27B-IT
Septor Labs5---free · shared daily allowanceMiniMax M2.5 (Septor Labs)
minimax-m2.5-free
Agnes AI4---free · promo $0/tokenAgnes 3.0 Flash (Agnes AI)
agnes-3.0-flash
Aion Labs415-20,000free · 20k tok/dayAion 3.0
aion-labs/aion-3.0
BlockRun4---Ongoing $0 models · rate-limited · no monthly cash grantMuse Glimmer 30B (BlockRun)
nvidia/muse-glimmer-30b
CLōD4---free · shared daily allowanceGemma 4 31B IT (CLōD)
Gemma 4 31B IT
LLM7440--Free tier: 100,000 tokens/24h sharedgpt-oss:20b (LLM7)
gpt-oss:20b
LLMTR4---Ongoing zero-priced routeQwen3.8 27B (LLMTR)
qwen/qwen3.8-27b-free
Router94---10,000 credits/month (~$1), shared; account-anniversary resetDeepSeek V4 Flash 0731 (Router9)
deepseek/deepseek-v4-flash
BazaarLink31050-free · shared rate limitDeepSeek V4 Flash (BazaarLink free)
deepseek/deepseek-v4-flash-0731free:free
BlazeAPI3---Free · 200,000 shared tokens/day; resets dailyGLM 5.3 Flash (BlazeAPI)
free/glm-5.3-flash
Zhipu AI3---~30MGLM-4.7 Flash
glm-4.7-flash
AMD Radeon Cloud2---free · recurring daily account allowanceQwen3.8 Flash Next (AMD Radeon Cloud)
Qwen3.8-Flash-Next
Logfare2---free · fair use · traffic loggedGemma 4 26B (Logfare)
gemma-4-26b
Moondream2---$5/month shared workspace usage creditsMoondream 3.1 9B A2B
moondream3.1-9B-A2B
Plugsky2---Ongoing Free plan; shared fair usePlugsky Micro
plugsky-micro
SimpleLLM2---Shared hourly/daily free-model quotaGemma E4B Free (SimpleLLM)
free-gemma-4-E4B
Speechify2----Simba 3.2 (Speechify)
simba-3.2
UnoRouter21--free · 1 req/min per modelGLM 5.3 (UnoRouter free)
glm-5.3:free
Free.ai1----Kokoro (Free.ai)
kokoro
Pollinations1----DreamShaper 8 LCM (Pollinations, legacy sana alias)
sana
Typhoon1---Ongoing free research API (shared rate limits)Typhoon 2.5 30B A3B Instruct
typhoon-v2.5-30b-a3b-instruct

Live data from the FreeLLMAPI catalog (version 2026.11.19, checked 19 November 2026). Free limits change often. The catalog is checked every day.

The catalog has 487 free model endpoints from 45 providers today. The values change often. Providers add models, remove models and change quotas without notice.

How to read RPM, RPD, TPM and TPD

Common rate limit names
LimitMeaningUsual window
RPMRequests per minuteA rolling 60 seconds
RPDRequests per dayOne day. The reset time is different for each provider.
TPMTokens per minute. Input and output tokens can both count.A rolling 60 seconds
TPDTokens per dayOne day
Monthly budgetAn estimate of the free tokens in one monthOne calendar month

The limit that stops you first is the one that matters. For example, Groq documents 30 RPM, 1,000 RPD, 8,000 TPM and 200,000 TPD for openai/gpt-oss-120b on its free plan. At 30 requests per minute you use the daily 1,000 requests in about 34 minutes. A request with 9,000 tokens fails at once, because it is larger than the 8,000 TPM limit.

  • Scope: Google applies Gemini limits to each Google Cloud project, not to each key. Groq applies limits to each organization. A second key in the same project or organization does not add quota.
  • Reset time: Google resets requests per day at midnight Pacific time. Cloudflare resets its daily allocation at 00:00 UTC.
  • Shared pools: some providers count one quota across all free models. OpenRouter counts the free daily requests across every :free model on the account.
  • Other units: Cloudflare Workers AI counts neurons, not tokens. The free allocation is 10,000 neurons per day.

Verified limits for the main providers

These values come from each provider's own documentation, checked on 20 November 2026. Use the live table above for model-level values.

Free limits from provider documentation
ProviderFree limit (official)Scope
Google AI Studio (Gemini)Different for each model. Google shows your active limits in AI Studio.Per Google Cloud project
Groqopenai/gpt-oss-120b: 30 RPM, 1,000 RPD, 8,000 TPM, 200,000 TPDPer organization
OpenRouter:free models: 20 RPM. 50 requests per day, or 1,000 per day after you buy 10 credits.Per account, all free models together
Cloudflare Workers AI10,000 neurons per day on Workers FreePer account
OVHcloud AI EndpointsAnonymous: 2 requests per minute. With a key: 400 requests per minute.Anonymous: per IP and model. Key: per project and model.
NVIDIA API CatalogNVIDIA does not publish the values. Your limit shows in your account on build.nvidia.com.Per account
CohereTrial keys: 20 requests per minute on chat models, 1,000 API calls per monthPer trial key
Note: NVIDIA free accounts commonly report a limit of 40 requests per minute. NVIDIA staff say that the limits are different for each model and that NVIDIA does not publish them. Read NVIDIA NIM rate limit for the details.

How to stack free tiers

One free tier is small. Many free tiers together give more requests per day. To stack them, get one key from each provider. Then send each request to a provider that still has quota.

FreeLLMAPI does this for you. It is an open-source gateway that runs on your computer. It keeps four counters (RPM, RPD, TPM, TPD) for each platform, model and key. Before it sends a request, it checks all four counters. It also checks pools that cover a whole account, for example the OpenRouter daily cap and the Cloudflare neuron cap.

Install and send one request

curl -fsSL https://freellmapi.co/install.sh | bash

curl http://localhost:3001/v1/chat/completions \
  -H "Authorization: Bearer <unified-key>" \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "hi"}]}'

Add your provider keys on the Keys page of the dashboard at http://localhost:3001. Copy the unified key from the same page. The response header X-Routed-Via shows the provider and the model that answered.

What happens at the limit

Most providers send HTTP 429 when you go over a limit. Some providers send a Retry-After header. FreeLLMAPI uses these signals in this sequence:

  1. A short 429 on a minute limit puts the key on a 90 second cooldown. The router tries the next model in the chain.
  2. A full daily quota puts the model and key on a longer cooldown: 2 minutes, then 10 minutes, then 1 hour, then 24 hours.
  3. If the provider gives a Retry-After value that is longer, the router uses the provider value.
  4. If an error body states the real limit, the router saves it. The next pre-check then stops the request before the provider rejects it.

When every key is on cooldown, the gateway returns 429. Free tiers have no SLA. The strongest free models often have the smallest daily caps, so the answer quality can go down late in the day.

Ways to get more requests per day

  • Add keys from more providers. Each provider adds its own quota.
  • Use small, fast models for simple tasks. Keep the large models with small daily caps for hard tasks.
  • Send fewer tokens. A shorter prompt helps with TPM and TPD limits.
  • Do not make many accounts with one provider to get more quota. Read the terms of each provider first. Many terms do not allow this.
  • Read free LLM API commercial use before you use free tiers in a product.
Use every one of these through one key. FreeLLMAPI is an open-source, self-hosted router that puts all these free tiers behind a single OpenAI-compatible endpoint and fails over when one is rate-limited. Browse the catalog or go live.

Frequently asked questions

What are the rate limits of the free Gemini API?

Google sets different limits for each model and applies them to each Google Cloud project. Your active limits show in AI Studio. Requests per day reset at midnight Pacific time. The live table on this page shows the current catalog values.

What is the Groq free tier rate limit?

Groq lists limits for each model. For openai/gpt-oss-120b the free plan allows 30 requests per minute, 1,000 requests per day, 8,000 tokens per minute and 200,000 tokens per day. Limits apply to the whole organization.

Does a second API key double my free quota?

Usually no. Google counts limits per project and Groq counts them per organization. A new key in the same project or organization shares the same quota.

Which free LLM API has the highest rate limit?

It depends on the limit type. Some providers give many requests per minute but few per day. Sort the live table by the limit that stops your workload first, then stack several providers.

What does error 429 mean on a free LLM API?

It means that you went over a rate limit or a quota. Wait for the reset time, send fewer tokens, or send the request to a different provider.

Sources

All guides · Browse all free models

Keep reading

All posts →
Guide

Best free LLM APIs 2026

Ten genuinely free LLM APIs worth using — ranked, with real limits.

Guide

Unlimited free AI tokens?

No free AI API is unlimited. The closest real thing: 10.1 billion free tokens a month behind one key.

Guide

How to get a free LLM API key

Get a working key in minutes — no credit card required.