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

BazaarLink free tier

🧭 Aggregators (one key, many providers) · no card · live — last verified by a probe on 2026-11-02 · bazaarlink.ai · back to the whole list

What you get

OpenAI-compatible gateway with a shared free allowance on selected models and an auto:free router

Free models

deepseek-v4-flash, nemotron-3.5-lightning

Limits, in the vendor’s words

Without credit: 10 requests/rolling minute; 60 weighted units/day per account

With credit: 20 requests/rolling minute; 120 weighted units/day per account

Free models: 2 requests at once per account

Free models: 20 requests/minute shared across the endpoint

Additional IP guard: Requests allowance: amount not published (period not published) per IP

The free models share each account’s daily weighted allowance, reset at 00:00 UTC. Longer inputs can consume more units. Account concurrency and the site-wide rate also apply. Paid fallback happens only when enabled and the account has sufficient credit. Free IDs and their metered twins are separate catalog routes.

Where it is offered

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

Connect

Base URL: https://api.bazaarlink.ai/v1
Key: BAZAARLINK_API_KEY — get one at https://bazaarlink.ai/keys
Callable ids: deepseek/deepseek-v4-flash-0731free:free, auto:free, nvidia/nemotron-3.5-lightning-free:free, reflection/beam-free:free, stealth/glyph-cluster:free, qwen/qwen3.7-flash:free
Note: The listed :free routes use the shared free allowance. auto:free selects a free model and can use paid routing on a funded account “unless paid fallback is disabled”. Glyph Cluster is a stealth model with an undisclosed identity.

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

curl -s https://api.bazaarlink.ai/v1/chat/completions \
  -H "Authorization: Bearer $BAZAARLINK_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"deepseek/deepseek-v4-flash-0731free:free","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'

Evidence

Probe: the models catalog at https://api.bazaarlink.ai/v1/models, free rows carrying :free, each listed family checked for a zero price
Source: https://bazaarlink.ai/free
Source: https://bazaarlink.ai/en/docs

History

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

2026-11-02 — Free models changed: added nemotron-3.5-lightning
2026-10-19 — Free models changed: dropped qwen3.7-flash
2026-09-28 — Free models changed: added deepseek-v4-flash
2026-08-19 — Free models changed: dropped deepseek-v4-flash
2026-08-03 — Added: OpenAI-compatible gateway to 199 models, with two always-free open models and an auto:free router

Generated from registry.yaml on 2026-11-02 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.