Qwen 4 Max:thinking API
Alibaba's Qwen 4 Max:thinking costs $1.41 per million input tokens and $4.24 per million output tokens from 1 supplier. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send qwen4-max:thinking as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About Qwen 4 Max:thinking
Qwen 4 Max:thinking is a language model from Alibaba. It takes text, images and video and gives text. The largest offer takes 1,000,000 input tokens. It has 1 supplier on this exchange now.
Facts
- Model name
- qwen4-max:thinking
- Maker
- Alibaba
- Context window
- 1M tokens
- Input price
- $1.41 per million tokens
- Output price
- $4.24 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $1.41 input and $4.24 output per million tokens, $0.071 cache read per million tokens, 1M tokens of context
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen4-max:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Qwen 4 Max:thinking?
- Qwen 4 Max:thinking is a language model from Alibaba.
- How much does Qwen 4 Max:thinking cost?
- Offers now ask $1.41 per million input tokens and $4.24 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of Qwen 4 Max:thinking?
- The largest offer takes 1,000,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Qwen 4 Max:thinking do?
- Its providers list Vision, Video input, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Qwen 4 Max:thinking support?
- Text · Images · Video → Text.
- Which providers serve Qwen 4 Max:thinking?
- It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
- How do I call Qwen 4 Max:thinking?
- Send "qwen4-max:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Qwen 4 Max:thinking listed?
- The exchange first listed it on 11/18/2026. This is not its release date.
Related pages
- Qwen 3.8 27B
- Qwen 3.6 35B a3b
- Qwen 3 14B
- Qwen 3 5 4B
- Qwen 3.5 9B
- Qwen 2.5 7B Instruct
- Popular open weights
- Reasoning models
- Set up a client
- All models
- Providers
- Discover the best model for your budget
- Quickstart
- llms.txt: the index of every page, as Markdown
- llms-full.txt: every page in one file
- This page as Markdown