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.
Modalities
Pricing Breakdown
| Type | Rate |
|---|---|
| Prompts up to 256K tokens | |
| Input | $0.054 / 1M tokens |
| Output | $0.432 / 1M tokens |
| Cached input | $0.054 / 1M tokens |
| Prompts over 256K tokens | |
| Input | $0.270 / 1M tokens |
| Output | $2.16 / 1M tokens |
| Cached input | $0.270 / 1M tokens |
Tiered pricing: when a request's prompt (input, cached tokens included) is over 256K tokens, every token in that request is billed at the long-context rates; exactly 256K is still the base rate. This model publishes no separate cached-input price: cached tokens are billed at the input rate of their group (the "Cached input" row shows that rate).
Supported Parameters
API Usage Examples
Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.
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."}
]
}'