Back to Models
Qwen Flash
qwenqwen/qwen-flash
Ultra-low-cost Qwen tier β steep discount on both directions.
qwen-flash is the cheapest commercial Qwen tier on Bailian. Same OpenAI-compatible surface, same 1M context, but priced for the bulk-processing end of the workload spectrum β $0.07 input / $0.50 output per MTok.
Treat it as the right default for background jobs and asynchronous pipelines: log enrichment, embedding pre-processing, large-scale rewriting, or any workload where you measure cost per million requests instead of per call.
Lowest commercial price
$0.07 input / $0.50 output per MTok β the floor of the Qwen commercial line.
1M context retained
Same long-context capability as qwen-turbo / qwen-plus β no chunking required for most jobs.
Bulk-friendly
Designed to absorb high-RPS batch traffic. Great default for offline pipelines.
Dual-region routing
Selector picks bailian-cn or bailian-sg per request based on cost.
When to use
Offline batch jobs, log enrichment, large-scale rewriting, tagging, embedding pre-processing β anywhere quality is acceptable and cost per million requests is the binding constraint.
When not to use
User-facing chat where reasoning quality matters, complex coding, or anything with measurable downstream business impact β use qwen-plus or above.
Pricing: $0.07 input / $0.50 output per MTok. TheRouter routes to the cheaper of bailian-cn / bailian-sg per request.
Context Length
1.0M
Max Output
33K
Input Priceper 1M tokens
$0.084/ 1M tokens
Output Priceper 1M tokens
$0.600/ 1M tokens
Modalities
textβtext
Pricing Breakdown
| Type | Rate |
|---|---|
| Input | $0.084 / 1M tokens |
| Output | $0.600 / 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/qwen-flash",
"messages": [
{"role": "user", "content": "Summarize the key points from this input."}
]
}'