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

SenseNova (SenseTime 商汤) free tier

🔌 LLM APIs with free tier · no card · offered only in mainland China · live — last verified by a probe on 2026-11-01 · sensenova.cn · back to the whole list

What you get

SenseTime’s SenseNova API, with a $0 Free plan during public beta; registration and identity verification required

Free models

sensenova-6.8-flash-lite

Limits, in the vendor’s words

Public beta: Usage allowance: amount not published (period not published) per account

Free during the public beta; paid tiers are planned. The Free card covers SenseNova 6.8 Flash Lite and SenseNova U1 Fast. Current numeric usage allowances and reset times are unpublished. The API guide calls the documented model an “early preview release” and requires “registration plus identity verification”. Up to 20 API keys are supported. Signup requires a phone number; acceptance of non-mainland numbers is unverified.

Where it is offered

Offered only in mainland China (source, read 2026-09-26). That leaves out 93.6% of the developers GitHub counts, beyond the countries under comprehensive US embargo (Innovation Graph, 2026 Q1).

Connect

Base URL: https://token.sensenova.cn/v1
Key: SENSENOVA_API_KEY — get one at https://platform.sensenova.cn
Callable ids: sensenova-6.8-flash-lite
Note: An API ID for SenseNova U1 Fast has not been confirmed.

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

curl -s https://token.sensenova.cn/v1/chat/completions \
  -H "Authorization: Bearer $SENSENOVA_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"sensenova-6.8-flash-lite","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'

Evidence

Probe: the page at https://www.sensenova.cn/token-plan, anchored on 公测期完全免费开放，付费档位即将上线, SenseNova 6.8 Flash Lite
Source: https://www.sensenova.cn/token-plan
Source: https://github.com/OpenSenseNova/SenseNova6.8/blob/main/API.md

History

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

2026-10-12 — Free models changed: added sensenova-6.8-flash-lite
2026-08-14 — Added: SenseTime’s own models plus DeepSeek and GLM behind an OpenAI-compatible url, free for everyone while the token plan is in public beta

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.