Qwen 3.8 Max:thinking API
Alibaba's Qwen 3.8 Max:thinking costs $2 per million input tokens and $6.01 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 qwen3.8-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 3.8 Max:thinking
Qwen 3.8 Max:thinking is a language model from Alibaba. Its release date is 3 August 2026. 2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows. Its weights are not public. It takes text, files, images and video and gives text. The largest offer takes 991,000 input tokens. It has 1 supplier on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- qwen3.8-max:thinking
- Maker
- Alibaba
- Context window
- 991K tokens
- Input price
- $2 per million tokens
- Output price
- $6.01 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $2 input and $6.01 output per million tokens, $0.25 cache read per million tokens, 991K 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": "qwen3.8-max:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Qwen 3.8 Max:thinking?
- Qwen 3.8 Max:thinking is a language model from Alibaba. Its release date is 3 August 2026. 2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows. Its weights are not public.
- How much does Qwen 3.8 Max:thinking cost?
- Offers now ask $2 per million input tokens and $6.01 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 3.8 Max:thinking?
- The largest offer takes 991,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Qwen 3.8 Max:thinking do?
- Its providers list Documents, 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 3.8 Max:thinking support?
- Text · Files · Images · Video → Text.
- Which providers serve Qwen 3.8 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 3.8 Max:thinking?
- Send "qwen3.8-max:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Qwen 3.8 Max:thinking released?
- Its creator released it on 3 August 2026.
- When was Qwen 3.8 Max:thinking listed?
- The exchange first listed it on 10/10/2026. 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