Back to Models
Qwen3 Max
qwenqwen/qwen3-max
Flagship Qwen3 β top-tier reasoning and coding from Alibaba.
qwen3-max is Alibaba's flagship commercial model in the Qwen3 generation. It leads the Qwen lineup on reasoning, coding, math, and complex tool use, with a 256K context window for repo-scale code, long documents, and multi-turn agent traces.
TheRouter ships this model on both the mainland (bailian-cn) and Singapore (bailian-sg) Bailian endpoints. The selector picks the cheaper region per request so you get vendor-direct latency without manual region pinning.
Deep reasoning
Best-in-family reasoning, math, and tool-use scores. Comfortable with chain-of-thought-heavy prompts.
256K context
Fits a small repo or several long PDFs in a single request β no chunking gymnastics required.
Dual-region routing
Auto-selects between bailian-cn and bailian-sg per request based on cost β no client-side region logic.
OpenAI-compatible
Standard `/v1/chat/completions` shape including tools, JSON mode, and streaming.
When to use
High-stakes reasoning, complex coding tasks, repo-aware refactors, and agent workloads where Qwen-family quality matters and budget allows for a flagship-tier model.
When not to use
High-volume customer support, simple rewrites, or latency-critical autocomplete β drop down to qwen-plus or qwen-turbo for 10β20Γ lower cost.
Pricing: $1.50 input / $7.50 output per MTok. TheRouter routes to the cheaper of bailian-cn / bailian-sg per request.
Context Length
262K
Max Output
33K
Input Priceper 1M tokens
$1.80/ 1M tokens
Output Priceper 1M tokens
$9.00/ 1M tokens
Modalities
textβtext
Pricing Breakdown
| Type | Rate |
|---|---|
| Input | $1.80 / 1M tokens |
| Output | $9.00 / 1M tokens |
Supported Parameters
temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop
API Usage Examples
Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.
cURL
curl https://api.therouter.ai/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $THE_ROUTER_API_KEY" -d '{
"model": "qwen/qwen3-max",
"messages": [
{"role": "user", "content": "Summarize the key points from this input."}
]
}'