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

Logfare (Standard models) free tier

🧭 Aggregators (one key, many providers) · no card · provisional — added on 2026-11-11, a regular row from the first probe it passes on or after 2026-11-25 · live — last verified by a probe on 2026-11-12 · logfare.ai · back to the whole list

What you get

Free OpenAI-compatible model gateway operated by Solexsis Research LLC, with a Standard tier and optional data-consent tiers

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

Regular account: 5,000 requests/day; 6 requests at once per account

Premium account: 10,000 requests/day; 12 requests at once per account

Pro account: 20,000 requests/day; 24 requests at once per account

New account: 500 requests/day; 2 requests at once per account

Shared network / IP: 40,000 requests/day per IP

One account per person; Discord verification and continued server membership are required. New-account limits apply for the first 24 hours. Account limits are shared across models, keys and apps; minute/hour, network and provider caps also apply. Some Standard models bypass request allowances, while concurrency and provider caps remain. Automation is allowed; honor Retry-After on 429/503. Standard traffic is logged for internal evaluation, with an evaluation opt-out. Optional Premium requires training consent; Pro additionally requires data-sale consent. Raw prompts reach changing upstream providers under their own policies. The privacy policy says API keys are stored in plain text, while current docs describe fingerprints only.

Where it is offered

The vendor names no country it keeps the offer from (source, read 2026-11-11).

What happens to what you send

What you send may be used to train or improve models. In the vendor’s words: “If — and only if — you opt in at /consent, your post-scrub request and response content may also be used to train and fine-tune the models we operate.” (source).

Connect

Base URL: https://logfare.ai/v1
Key: LOGFARE_API_KEY — get one at https://logfare.ai/register
Anthropic-format base (Claude Code’s ANTHROPIC_BASE_URL): https://logfare.ai
Callable ids: economy/deepseek-v4.1-flash, gemma-4-26b, gemma-4-31b-it, qwen-3.8-27b
Note: These IDs use Standard access without training or data-sale opt-in. Register, link your Discord account and keep server membership; each API key is shown once. Use /chat/completions for chat, tools and streaming, or the documented /v1/messages route. Premium and Pro models need separate data consents and are not configured here.

Try it from your terminal with your key in LOGFARE_API_KEY — it goes from your machine to the vendor and nowhere else:

curl -s https://logfare.ai/v1/chat/completions \
  -H "Authorization: Bearer $LOGFARE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"qwen-3.8-27b","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'

Evidence

Probe: the page at https://logfare.ai/docs, anchored on There are three tiers, and every one is free, New accounts use the new-account budget for their first 24 hours; ids checked in https://logfare.ai/v1/models
Source: https://logfare.ai/
Source: https://logfare.ai/docs
Source: https://logfare.ai/v1/models
Source: https://logfare.ai/tos
Source: https://logfare.ai/privacy
Source: https://logfare.ai/register

History

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

2026-11-11 — Added: Free OpenAI-compatible model gateway operated by Solexsis Research LLC, with a Standard tier and optional data-consent tiers

Generated from registry.yaml on 2026-11-12 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.