Free LLM APIs
Providers that let you call a large language model without paying. Some are free forever, some hand out signup credits, and some are limited-time offers — rated 0-5 on quota, rate limits and stability to help you pick quickly.
Free tiers usually come with strict limits. They are best suited to development, prototyping and testing — we do not recommend relying on them in production.
Quota, rate limit and stability ratings are subjective assessments by the site editors based on hands-on testing. They are indicative only — always check the provider's own documentation for the actual terms.
8 active entries
Google AI Studio
United States
Quota★★★★☆
Rate limits★★★★☆
Stability★★★★☆
Google AI Studio provides a free tier for Gemini models on each account, with request quotas reset daily. Different models have different limits; please refer to the actual limits for specifics.
- Gemini 3.8 Flash
- Gemini 3.5 Flash Lite
- Gemma 4 31B
Checked Sep 23, 2026
Ollama Cloud
United States
Quota★★★★☆
Rate limits★★★★☆
Stability★★★★☆
Some of Ollama's cloud models offer a certain amount of free quota, with relatively relaxed QPS limits, and the quota resets every two weeks. Registration may require overseas phone number verification.
- gpt-oss:120b
- gemma4:31b
- gpt-oss:20b
Checked Sep 23, 2026
OpenRouter
United States
Quota★★★★☆
Rate limits★★★★☆
Stability★★★★☆
A unified entry point aggregating hundreds of models. Only models marked with the :free suffix can be used for free. Providers often offer limited-time free access to new models on OpenRouter, but free models may be slower and less stable.
- gemma-4-31b-it:free
- glm-5.2:free
Checked Sep 23, 2026
Cloudflare Workers AI
United States
Quota★★★☆☆
Rate limits★★★☆☆
Stability★★★☆☆
Each Cloudflare account gets 10k neurons free per day, can call some open-source models, a bit complex to get started, average speed.
- glm-5.3-flash
- qwen3.8-27b
- deepseek-v4-flash-0731
AMD Radeon Cloud
United States
Quota★★★☆☆
Rate limits★★★☆☆
Stability★★★☆☆
AMD Radeon Cloud is a free shared LLM API service provided by AMD for developers, compatible with the OpenAI interface. Due to the large number of users, speed and stability are average.
- DeepSeek-V4.1-Flash
- GLM-5.3-Flash
- Qwen3.8-27B
Checked Sep 23, 2026
NVIDIA NIM
United States
Quota★★★☆☆
Rate limits★★★☆☆
Stability★★☆☆☆
NVIDIA's official free large model service, requires mobile phone verification during registration, has relatively strict quotas, and moderate stability.
- deepseek-v4.1-flash
- glm-5.3-flash
Checked Sep 23, 2026
Groq
United States
Quota★★☆☆☆
Rate limits★★★★☆
Stability★★★☆☆
Groq is an American AI chip and cloud service company (not Musk's Grok, mind you), known for its LPU chips designed to accelerate large-model inference and its high-speed inference cloud platform. It offers free quotas for some open-source models; the speed is very fast, but the quota is relatively small, the models are relatively old, and it resets once a day.
Checked Sep 23, 2026
Frequently asked questions
- Are these free APIs really free?
- They all have a genuinely free way to call the API, but the terms differ: some are free indefinitely at a low rate limit, some give one-off signup credits, and some are promotions that expire. Always confirm the current terms on the provider's own pricing page before relying on one.
- Why do quotas and rate limits keep changing?
- Free tiers are promotional, so providers adjust or withdraw them without notice. We re-check entries periodically and record the last update date on each card. If you spot something outdated, treat the official pricing page as the source of truth.
- Do I need a credit card or VPN?
- It varies by provider. Some require a phone number or a linked payment method even to use the free tier; others need a VPN depending on where you are. Check the provider's signup requirements before committing.
- How are the star ratings decided?
- Ratings are an editorial summary, not a benchmark. Quota reflects how much you get, rate limits reflect how strict the throttling is (more stars means looser), and stability reflects how reliably the endpoint responds in practice. They are meant for quick scanning — read the description for specifics.
About this directory
We collect publicly documented free tiers, signup credits and limited-time offers from LLM providers, then summarise what you get and how usable it is. It is manually curated and updated as offers change.
Unofficial directory, not affiliated with any provider listed. Free offers change frequently and may be region-restricted. Always verify the current terms on the provider's own website — the link on each card is the authoritative source.