TheRouter.aiTheRouter.ai
Back to Models

Qwen Plus

qwenqwen/qwen-plus

Mid-tier Qwen with thinking + non-thinking modes and 1M context.

qwen-plus is the workhorse of the Qwen3 commercial line. It offers two operating modes — fast `enable_thinking: false` for everyday chat and a deeper `enable_thinking: true` mode that emits `reasoning_content` for harder problems — at a fraction of the flagship's price.

The 1M context window makes it a strong default for long-document Q&A, multi-file code reading, and long agent conversations. TheRouter routes between bailian-cn and bailian-sg per request based on cost; `enable_thinking` and `reasoning_content` pass through verbatim in both directions.

Thinking + non-thinking
Toggle `enable_thinking` per request. When true, the model returns a `reasoning_content` field alongside the final answer.
1M context
One of the largest commercial Qwen context windows — ideal for whole-doc or multi-file workloads.
Cost-balanced
$0.50 input / $1.50 output per MTok. ~5× cheaper than qwen-max on input, ~5.3× cheaper on output.
Dual-region routing
Selector picks the cheaper of bailian-cn / bailian-sg per request — no client-side region logic.
When to use
Default Qwen model for production: long-document Q&A, multi-step agents, code reading, and chat where you want optional deeper reasoning without paying flagship prices.
When not to use
If you need the absolute best Qwen reasoning or coding, step up to qwen3-max / qwen3-coder-plus. For high-throughput cheap chat, qwen-turbo or qwen-flash is more cost-effective.
Pricing: $0.50 input / $1.50 output per MTok. TheRouter routes to the cheaper of bailian-cn / bailian-sg per request. Thinking mode does not change the price.
Context Length
1.0M
Max Output
33K
Input Priceper 1M tokens
$0.600/ 1M tokens
Output Priceper 1M tokens
$1.80/ 1M tokens

Modalities

text→text

Pricing Breakdown

TypeRate
Input$0.600 / 1M tokens
Output$1.80 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatreasoningstop

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/qwen-plus",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'
Customer Support