awesome-free-ai-coding · every free model · every provider · filter the list

Arli AI free tier

🔌 LLM APIs with free tier · no card · live — last verified by a probe on 2026-11-01 · arliai.com · back to the whole list

What you get

OpenAI-compatible inference on open models and their fine-tunes, whose Free plan tries each model five times every two days at 12K tokens of context, one request at a time

Free models

No free model family is currently listed here; callable ids, where the row has them, are under Connect.

Limits, in the vendor’s words

5 requests/2 days per account per model

1 request at once per account

Free is for testing, with delayed responses, slower service as use increases and a 12K context limit. Its catalog includes many roleplay and writing fine-tunes alongside coding-capable base models. Continuing beyond the trial allowance requires a paid plan.

Where it is offered

The vendor names no country it keeps the offer from (source, read 2026-09-26).

What happens to what you send

What you send is not used to train models. In the vendor’s words: “By submitting prompts or other inputs to the Services, you grant us a worldwide, non-exclusive, royalty-free license to use, process, and transmit your inputs solely for the purpose of generating and returning a response to you, and only for the duration necessary to complete that request.” (source).

Connect

• Base URL: https://api.arliai.com/v1
• Key: ARLI_AI_API_KEY — get one at https://www.arliai.com/account
• Callable ids: none listed — its public catalog names models by display name, and /v1/models, which holds the ids a request carries, answers only a key
• Note: Choose an exact ID from the model catalog. The coding quickstart covers Roo Code and Kilo Code; set the context window for the selected model. Chat completions require an API key.

Check your key from your terminal — with it in ARLI_AI_API_KEY, the vendor’s catalog lists the models it can call:

curl -s https://api.arliai.com/v1/models \
  -H "Authorization: Bearer $ARLI_AI_API_KEY"

Evidence

• Probe: the page at https://www.arliai.com/docs/textgen, anchored on Free accounts are able to use each model for a maximum of 5 requests every 2 days
• Source: https://www.arliai.com/pricing
• Source: https://www.arliai.com/docs/textgen
• Source: https://www.arliai.com/quick-start
• Source: https://api.arliai.com/model/all

History

Each line is a change to what this page publishes, dated the day it reached the list, in UTC.

• 2026-09-17 — Added: OpenAI-compatible inference on open models and their fine-tunes, whose Free plan tries each model five times every two days at 12K tokens of context, one request at a time

---

Generated 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.

Something wrong or missing? Suggest a service or a change — or read how the list works.