Pricing
Pay-as-you-go, metered per call. Currency: CNY per million tokens. Balance never expires.
Input tokens
¥8.00
Per million tokens · the prompts and context you send to the model
Output tokens
¥28.00
Per million tokens · text generated by the model (output priced at 3.5× input)
Cache hit (read)
¥2.00
Vendor list cache price · keep the system prompt stable to hit the cache
Cache hits cost less: ¥2.00 per million (about 1/4 of the input price) — save about 75% on repeated prefixes
Live pricing follows GET /v1/models responses; the console itemizes the input, output and cached tokens of every call.
Capabilities & use cases
Overview
All of the gains in GLM-5.3 come from post-training, with coding 50% better than 5.2 — the strongest open model; GLM-5.2 is the MIT-licensed flagship with a true 1M context, natively optimized for Chinese.
Key strengths
Natively optimized for ChineseOpen source, commercially usableStronger coding1M context
Recommended use cases
Chinese coding tasks and projects that need an open-source, commercially usable option.
Example call
Fully OpenAI-compatible — just point base_url at ShinLinkAI. No changes to your application code.
curl
curl https://api.shinloo.com/v1/chat/completions \
-H "Authorization: Bearer sk-sl-…" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3",
"messages": [{"role": "user", "content": "Hello"}]
}'