Pricing
Metered per token, billed per call. Unit: CNY per million tokens. Balance never expires.
Input tokens
¥0.80
Per million tokens · the prompt and context you send to the model
Output tokens
¥2.70
Per million tokens · text generated by the model (output is 3.4× the input price)
Cached input (read)
¥0.10
Vendor list cache price · keep the system prompt stable to hit the cache
Cache hits cost less: ¥0.10 per million (about 1/8 of the input price) — save about 88% on repeated prefixes
Live pricing is governed by the GET /v1/models response; the console itemizes input, output and cached tokens for every call.
Capabilities
Overview
The Qwen 3.8 family: Qwen3.8-Max is a 2.4T-parameter open-source MoE flagship that can code and deliver complete projects spanning 10+ days on its own; Flash activates only 6B parameters per token yet carries a 1M context — outstanding value.
Key strengths
Extra-long contextStrong Chinese understandingVision understandingLowest unit cost
Best for
High-concurrency calls, simple Q&A, classification and extraction, and anything extremely cost-sensitive.
Example call
Fully OpenAI-compatible — point base_url at ShinLinkAI and change nothing else in your code.
curl
curl https://api.shinloo.com/v1/chat/completions \
-H "Authorization: Bearer sk-sl-…" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'