Pricing
Pay-as-you-go, metered per call. Currency: CNY per million tokens. Balance never expires.
Input tokens
¥4.20
Per million tokens · the prompts and context you send to the model
Output tokens
¥16.80
Per million tokens · text generated by the model (output priced at 4.0× input)
Cache hit (read)
¥0.84
Vendor list cache price · keep the system prompt stable to hit the cache
Tiered input pricing
Input ≤512K: in ¥4.20 / out ¥16.80 / cache hit ¥0.84 per 1M tokens; input >512K: in ¥8.40 / out ¥33.60 / cache hit ¥1.68
Cache hits cost less: ¥0.84 per million (about 1/5 of the input price) — save about 80% 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
MiniMax-M3 is live on the ShinLinkAI gateway and supports image understanding: read screenshots and documents, OCR, analyze photos. Input price ¥4.20 / 1M tokens (for input ≤512K; input >512K uses the higher tier).
Key strengths
Image understandingScreenshot recognitionDocument understandingOCR
Recommended use cases
Screenshot Q&A, document and photo understanding, and mixed text-and-image conversations.
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": "minimax-m3",
"messages": [{"role": "user", "content": "Hello"}]
}'
More models from this vendor
No other chat models from this vendor yet.