Qwen3.6 Plus API

Qwen3.6-Plus is a native vision-language model with image, text and video input, a 1M context and a 65K output ceiling. Alibaba highlights Agentic coding, frontend work, OCR, object localization and multimodal recognition.

Context 1MMax output 66KFrom ¥1.6 / ¥9.6 input/output

Official source: model page · verified 2026-10-22

Create an account Read the docs

PRICING

Pricing

CNY / usage-based

TierInput / 1MCached / 1MOutput / 1M

Input ≤ 256K¥1.6—¥9.6

Input > 256K¥6.4—¥38.4

Prices can change with upstream providers; the rate at settlement is authoritative.

QUICKSTART

Call the API

Use the OpenAI-compatible endpoint; no model-specific SDK setup is required.

Shell

curl https://api.kimiseek.app/v1/chat/completions \
  -H "Authorization: Bearer $KIMISEEK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.6-plus",
    "messages": [{"role": "user", "content": "Hello from KimiSeek"}]
  }'

FIT

Where it fits

Best for

Vision-heavy extraction and OCR
Frontend and Agentic coding
Long-context multimodal workflows on a budget

Tradeoffs

65K output ceiling is smaller than newer Plus and Max models
Older generation than Qwen3.7 and Qwen3.8

DETAILS

Model details

One API keyCNY billingOpenAI-compatiblePay as you go

FAQ

Does Qwen3.6-Plus accept video?

Yes. The official model page lists image, text and video input, with text output.

What is the main constraint?

The 65K maximum output is the practical limit for long deliverables.

How do I call this model?

Use KimiSeek's OpenAI-compatible API and set the model field to qwen3.6-plus with your KimiSeek API key.