Providers and ModelsAlibaba Cloud

Qwen3 Max Preview

Qwen3 Max Preview
Alibaba Cloud · Text Generation
POST /v1/chat/completions

Preview release with major gains over the 2.5 series in Chinese-English understanding, complex instructions, multilingual ability, and tool use.

This model is deprecated and will be retired on 2026-10-10. After that date, requests to this model will fail. Migrate to a successor model before then.

At a glance

FieldValue
Model idqwen3-max-preview
Model release date2025-09-05
Input modalitiesText
Output modalitiesText
Context window256K
Weight precision-
Max output tokens65,536
RegionSingapore
Featuresreasoning, code_interpreter, web_search
Native inferenceNo
NewNo
Structured outputJSON Mode
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/qwen3-max-preview:generateContent
Deprecation date2026-10-10

Pricing

ChargeSpecRate
Inputper 1M prompt tokens<=32K $1.08 (was $1.20); 32K-128K $2.16 (was $2.40); 128K-256K $2.70 (was $3.00)
Outputper 1M generated tokens<=32K $4.80 (was $6.00); 32K-128K $9.60 (was $12.00); 128K-256K $12.00 (was $15.00)
Web searchper call when invoked$0.015

Example request

$curl https://api.empiriolabs.ai/v1/chat/completions \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "qwen3-max-preview", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.7Sampling temperature. 0 is deterministic and 2 is maximum randomness. · Range: 0 – 2
top_pnumberno1.0Nucleus sampling probability mass. Lower values make outputs more focused. · Range: 0 – 1
max_tokensnumberno4096Maximum output tokens. · Range: 1 – 65536
stopstringno-Up to 4 strings where the model will stop generating further tokens.
enable_thinkingbooleannotrueEnable reasoning before answering.
frequency_penaltynumberno0Penalty based on how often a token has already appeared. · Range: -2 – 2
presence_penaltynumberno0Penalty for tokens that already appeared in the generated text. · Range: -2 – 2
tool_web_searchbooleannofalseSearch the web for real-time information. Adds $0.015 to the request cost for each invoked call.
tool_code_interpreterbooleannofalseRun Python code in a sandbox. Requires Thinking.
response_formatenumno-Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.
disable_formattingbooleannofalseSkip the EmpirioLabs Markdown formatting (citation [N] rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.

Notes

Deep thinking + code interpreter both available as opt-in toggles.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen3-max-preview.