Back to Models
QwQ Plus
qwenqwen/qwq-plus
Reasoning-focused Qwen β full thinking traces in every response.
qwq-plus is a reasoning-first model in the Qwen line. Unlike chat-tuned models, it always runs in thinking mode and returns its `reasoning_content` trace alongside the final answer β useful when you want to inspect or audit how the model arrived at a conclusion.
Use it on problems where reasoning quality is the deciding factor: math, multi-step planning, complex tool selection, and structured analytical tasks. TheRouter routes between bailian-cn and bailian-sg per request based on cost; `reasoning_content` passes through verbatim.
Always-on thinking
Returns `reasoning_content` on every response β no `enable_thinking` toggle required.
Reasoning specialist
Tuned for math, logic, planning, and multi-step tool selection over conversational chit-chat.
128K context
Enough context for full problem statements, prior reasoning traces, and tool results.
Dual-region routing
Selector picks bailian-cn or bailian-sg per request based on cost.
When to use
Math problems, multi-step planning, audit-friendly reasoning, complex tool selection, and analytical tasks where the thinking trace itself has value.
When not to use
Latency-critical chat, autocomplete, or any UX where the user does not benefit from the thinking trace β pick qwen-plus with thinking off, or qwen-turbo / qwen-flash.
Pricing: $1.00 input / $3.00 output per MTok. The `reasoning_content` tokens count toward output billing. TheRouter routes to the cheaper of bailian-cn / bailian-sg per request.
Context Length
131K
Max Output
33K
Input Priceper 1M tokens
$1.20/ 1M tokens
Output Priceper 1M tokens
$3.60/ 1M tokens
Modalities
textβtext
Pricing Breakdown
| Type | Rate |
|---|---|
| Input | $1.20 / 1M tokens |
| Output | $3.60 / 1M tokens |
Supported Parameters
temperaturemax_tokenstop_ptoolsresponse_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/qwq-plus",
"messages": [
{"role": "user", "content": "Summarize the key points from this input."}
]
}'