Skip to content
freellm.today

Find the free AI API that fits, before you sign up

Every free tier read on the provider’s own page, with the day it was read. Say what you need, see who qualifies, and test from your own browser that the API is up.

providers read
18
free models listed
41
need no card
4
APIs answering
9/9

Provider API status

9 of 9 answering

Asked from our server on 15 Oct, 02:47 UTC, with no key: any answer, even “key required”, means the server is up. Press Test to ask from your own network, or switch to the WebGPU tab to run a model locally.

All free models: free models with their limits, one row per model
ModelProviderInputContextReq / minReq / dayTokens / dayTest
openai/gpt-oss-120bGroqAnswering--301,000200K
openai/gpt-oss-20bGroqAnswering--301,000200K
qwen/qwen3.8-27bGroqAnswering--301,000200K
baidu/ernie-5.5-flash-preview:freeBaidu: ERNIE-5.5-Flash-PreviewOpenRouterAnsweringText1.02M2050-
google/gemma-4-26b-a4b-it:freeGoogle: Gemma 4 26B A4BOpenRouterAnsweringImage, Text, Video262K2050-
google/gemma-4-31b-it:freeGoogle: Gemma 4 31BOpenRouterAnsweringImage, Text, Video262K2050-
inclusionai/ling-3.2-flash:freeinclusionAI: Ling 3.2 FlashOpenRouterAnsweringImage, Text1.05M2050-
liquid/lfm-3-1.7b:freeLiquidAI: LFM3-1.7BOpenRouterAnsweringText262K2050-
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeNVIDIA: Nemotron 3 Nano OmniOpenRouterAnsweringAudio, Image, Text, Video256K2050-
nvidia/nemotron-3-ultra-550b-a55b:freeNVIDIA: Nemotron 3 UltraOpenRouterAnsweringText1M2050-
nvidia/nemotron-3.5-lightning:freeNVIDIA: Nemotron 3.5 LightningOpenRouterAnsweringText1M2050-
nvidia/nemotron-3.5-super-vl:freeNVIDIA: Nemotron 3.5 Super VLOpenRouterAnsweringImage, Text, Video1M2050-
particle-ai/particle-1:freeParticle AI: Particle-1OpenRouterAnsweringImage, Text1.05M2050-
recursive/flint-v1.0:freeRecursive: FlintOpenRouterAnsweringText262K2050-
DeepSeek-V3.1SambaNova CloudAnsweringText-2020200K
DeepSeek-V3.2SambaNova CloudAnsweringText-2020200K
gemma-4-31B-itSambaNova CloudAnsweringText-2020200K
gpt-oss-120bSambaNova CloudAnsweringText-2020200K
Meta-Llama-3.3-70B-InstructSambaNova CloudAnsweringText-2020200K
Free tier15 req/min · 20,000 tokens/min · 20,000 tokens/dayAion LabsAnswering--15-20K
Gemini 2.5 FlashGoogle Gemini APIAnswering-----
Gemini 2.5 Flash-LiteGoogle Gemini APIAnswering-----
Gemini 2.5 ProGoogle Gemini APIAnswering-----
Gemini 3 Flash PreviewGoogle Gemini APIAnswering-----
Gemini 3.1 Flash-LiteGoogle Gemini APIAnswering-----

A dash means the provider’s page does not state the figure. Where a provider states one limit for all its free models, the same figure is shown on each row.

All providers, line by line

Every value carries the day it was read. The check mark opens the provider’s own page. “Not published” means the page gives no figure, and we do not borrow one from elsewhere.

18 of 18 providers

Free LLM API tiers: limits and terms per provider, each with its source and check date
ProviderFree allowanceCard to startTrains on your dataCommercial useOpenAI SDKTest it
GroqFree tier
30 req/min · 1,000 req/day
1,000
Not verified since

Last value read: not published. Older than 30 days.

Not published
Not verified
Google Gemini APIFree tier
Not published
Not published
Not published
Not required
Restricted
OpenRouterFree tier
20 req/min · 50 req/day
Not required
Your setting
Not verified
Cloudflare Workers AIFree tier
10,000 Neurons/day
Not published
Not published
Not verified
Not verified since

Last value read: No. Older than 30 days.

Not verified
Hugging Face Inference ProvidersRetired
None
Not published
Not published
Not verified
Not verified
Not verified
NVIDIA NIMFree tier
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not verified
Not verified since

Last value read: Not for production. Older than 30 days.

Not verified
Not available
CerebrasTrial only
$5 trial credit, 30 days
Not verified since

Last value read: not published. Older than 30 days.

Required
Not verified
Not verified
GitHub ModelsRetired
Not published
Not published
Not published
Not published
Not published
Not published
Not published
Not available
Mistral La PlateformeFree tier
Not verified
Not verified
Not verified
Not verified
Not verified
Not verified
Not verified
Not available
CohereFree tier
Not verified since

Last value read: 20 req/min · 1,000 API calls/month. Older than 30 days.

Not verified since

Last value read: 20. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: Yes. Older than 30 days.

Ollama CloudFree tier
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not available
Z AIFree tier
Not verified
Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not verified
OVHcloud AI EndpointsFree tier
Anonymous: 2 req/min per IP and per model; with API key: 400 req/min per project and per model
Not verified
Required
Not verified since

Last value read: not published. Older than 30 days.

Not verified
Not verified
Not available
LLM7.ioFree tier
1 req/s · 60 req/min · 250 req/hour · 100,000 tokens/24h
Not verified
Not verified
Not verified since

Last value read: not published. Older than 30 days.

Not verified
Aion LabsFree tier
15 req/min · 20,000 tokens/min · 20,000 tokens/day
Not verified since

Last value read: not published. Older than 30 days.

Not required
Not verified since

Last value read: Allowed. Older than 30 days.

Kilo CodeFree tier
Not verified since

Last value read: 200 requests/hour per IP on free models. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Your setting
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not available
SambaNova CloudFree tier
20 req/min · 20 req/day · 200,000 tokens/day per model
Not required
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

TyphoonFree tier
5 req/s · 200 req/min per model
Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

Not verified since

Last value read: Yes. Older than 30 days.

Not verified since

Last value read: not published. Older than 30 days.

18 of 18 providers. Scroll the table sideways for all columns.

96 of 216 cells above were read on the provider’s own page in the last 30 days (oldest check: ). Each check mark opens that page. The other 120 say “not verified” instead of repeating a number from someone else’s article.

One request, any provider

Providers with a compatible endpoint take the same code. Switch the provider: only the base URL, the model id and the name of the key variable change. Base URLs side by side

Language
base_url
https://api.groq.com/openai/v1
model
openai/gpt-oss-120b
key from
$GROQ_API_KEY
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key=os.environ["GROQ_API_KEY"],
)

reply = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Reply with the word: ok"}],
)
print(reply.choices[0].message.content)
Endpoint read on · console.groq.com

The key is read from an environment variable on your machine. This site has no field for keys and never asks for one.

What changed lately

Free tiers get cut, turned into trials or retired. Each entry links to the page that confirms it.

  • · RetiredHugging Face Inference Providers no longer gives free accounts monthly credits
  • · ReducedGroq lowers the free limits of openai/gpt-oss-safeguard-20b
  • · RemovedGemini 3.7 Flash, 3.5 Flash and 3.1 Pro Preview are not free on the pricing page
  • · ReducedCerebras lists a time-limited trial, not a recurring free tier
Full change log, with sources

How to read a free tier

Four things that change what a “free” number is worth.

The unit changes from provider to provider

Groq and OpenRouter count requests. Groq also counts tokens per minute and per day, and for chat that is the limit you hit first. Cloudflare counts Neurons, its own unit of compute. Two free tiers cannot be ranked by one number; compare each against the traffic you expect.

The limit belongs to an account or a project

Google applies Gemini API limits per project, not per key. OpenRouter counts all free model variants of an account together. Creating more keys does not multiply a free allowance.

The terms cost more than the limit

A free tier is paid for in some other way: with your prompts, as on the Gemini API free tier, where content is used to improve Google products; or with a restriction, as on NVIDIA NIM, where free access stops at production. Read the data and commercial-use columns before the rate limit.

Free tiers end

GitHub Models was retired on 30 July 2026, and Hugging Face’s pricing page now lists no monthly credits for free accounts. Cerebras now describes a 30-day trial with a payment method where older articles describe a free tier. Keep the provider behind configuration, with a second one ready, and follow the change log.

Questions and answers

What people ask before they pick a free tier.

Which LLM APIs have a free tier right now?

On 2 Nov 2026 we confirmed a free offer on the official pages of Groq, Google Gemini API, OpenRouter, Cloudflare Workers AI, NVIDIA NIM, Mistral La Plateforme, Cohere, Ollama Cloud, Z AI, OVHcloud AI Endpoints, LLM7.io, Aion Labs, Kilo Code, SambaNova Cloud, Typhoon. Cerebras lists a 30-day trial with a payment method instead of a recurring free tier, Hugging Face no longer gives free accounts monthly credits, and GitHub Models was retired on 30 July 2026.

How do I know the limits on this page are current?

Every cell has a check mark with the day it was read and a link to the provider’s page. A weekly job opens each official page and looks for the registered value; only when it finds it does the date of that item move forward. After 30 days without a new check, the cell stops showing the value as current and says “not verified”. Your browser makes that calculation from today’s date.

Why do some cells say “not published”?

Because the provider’s own page does not state the value. Google, for example, does not list free-tier limits per model: its rate-limits page says they can be viewed in Google AI Studio. We print that instead of a figure taken from a third-party article.

Do I have to paste my API key here?

No. There is no field for a key anywhere on this site. The code sample reads the key from an environment variable on your computer.

Is a free tier enough for production?

Rarely. Free limits are low, can change without notice, and some terms exclude production: NVIDIA limits free NIM access to development, testing, research and evaluation, and Google requires paid services for apps offered to users in the EEA, Switzerland or the UK. Check the commercial-use column before building on one.

How often is the OpenRouter free model list updated?

It is read from the OpenRouter models API by a scheduled job once a day, and each page shows the collection time in UTC. The copy on this page was collected on 22 Nov 2026 and lists 14 zero-price models, 11 of them with an id ending in “:free”.