qwen3.7-flash
qwen3.7-flashAvailability100.0%
Available
Samples: 4
Output speed104.5 tok/s
Qwen3.7 Flash is a fast multimodal Qwen model with text, image, and video input, a 1M-token context window, tool use, and optional reasoning.
Total input tokens < 32,000
- Input
- $0.015/1M
- Output
- $0.065/1M
- Cache read
- $0.003/1M
- Cache write
- $0.019/1M
Total input tokens ≥ 32,000 and Total input tokens < 256,000
- Input
- $0.05/1M
- Output
- $0.2/1M
- Cache read
- $0.01/1M
- Cache write
- $0.0625/1M
Total input tokens ≥ 256,000
- Input
- $0.1/1M
- Output
- $0.4/1M
- Cache read
- $0.02/1M
- Cache write
- $0.125/1M
- Context window
- 1,000,000
- Route
- salesPlus routes
Roleplay
Not measuredNo matching public benchmark is available for this model.
Routes
Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.
| Use this model | ||||||
|---|---|---|---|---|---|---|
| origin | Total input tokens < 32,000
Total input tokens ≥ 32,000 and Total input tokens < 256,000
Total input tokens ≥ 256,000
| Not measured | Not measured | Plans and tiers | ||
| sales | Total input tokens < 32,000
Total input tokens ≥ 32,000 and Total input tokens < 256,000
Total input tokens ≥ 256,000
| Not measured | Not measured | Plans and tiers | ||
Quick start
Access and billingcurl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "qwen3.7-flash",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'