awesome-free-ai-coding · every free model · every provider · filter the list
🔌 LLM APIs with free tier · card required · not offered in Vietnam, Türkiye, Taiwan and 24 more places · live — last verified by a probe on 2026-11-01 · ibm.com · back to the whole list
IBM’s watsonx.ai Runtime on its Lite plan — 300,000 tokens a month of foundation-model inference (Granite, Llama, Mistral and other hosted models) on IBM Cloud, a plan IBM’s own docs call free and never bill
No free model family is currently listed here; callable ids, where the row has them, are under Connect.
Lite: 300,000 tokens/month; 2 requests/second per service plan
Lite compute: 20 CUH/month per service plan
The Lite service plan has limited capacity and no published expiry. IBM Cloud signup requires personal and card information to verify identity; Lite plans do not incur charges. Its covered foundation models are listed separately. The compute allowance and inference-token budget measure different kinds of usage.
Not offered in Vietnam, Türkiye, Taiwan, Nigeria, Ukraine, Egypt, Saudi Arabia, Switzerland and 19 more places (source, read 2026-09-26). That leaves out 10.2% of the developers GitHub counts, beyond the countries under comprehensive US embargo (Innovation Graph, 2026 Q1). In the vendor’s words: “The following table shows the countries where personal use of the platform not related to business, trade, craft, or professional purposes is not supported”.
What you send is not used to train models. In the vendor’s words: “IBM does not use your work to improve IBM models. … The foundation models are hosted in IBM Cloud or AWS; your prompts are not sent to third-party platforms.” (source).
https://us-south.ml.cloud.ibm.com/ml/v1 (not OpenAI-shaped)IBM_WATSONX_AI_API_KEY — get one at https://cloud.ibm.com/iam/apikeyswatsonx.ai Runtime and A free plan with limited capacity., 300,000 tokens per month, 20 CUH per month, 2 inference requests per second in the page’s own dataEach line is a change to what this page publishes, dated the day it reached the list, in UTC.
2026-09-05 — Added: IBM’s watsonx.ai Runtime on its Lite plan — 300,000 tokens a month of foundation-model inference (Granite, Llama, Mistral and other hosted models) on IBM Cloud, a plan IBM’s own docs call free and never billGenerated from registry.yaml on 2026-11-01 and re-verified twice a week; the full list, the Atom feed and the machinery are at https://github.com/mvalentsev/awesome-free-ai-coding.