Qwen-Flash
Qwen3 Flash combining thinking and non-thinking modes with dynamic switching.
Specs
- Context
- 1M
- Max output
- 32.8K
- Input price
- $0.05/ 1M tokens
- Output price
- $0.4/ 1M tokens
- Released
- 2025-08-01
Context
- Context window
- 1M
- Max input
- 998K
- Max output
- 32.8K
Pricing · USD / 1M tokens
- Input
- $0.05
- Output
- $0.4
- Cache read
- $0.005
- Cache write
- $0.063
Modalities
- Input
- Text
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Active
- Released
- 2025-08-01
- Knowledge cutoff
- —
Features
- Confirmed
How to call
1 provider
alibabamodel = qwen-flashreasoning = enable_thinking
chat
POSThttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
messages
POSThttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages
JSON
Standard format
{
"id": "qwen-flash",
"object": "model",
"created": 1754006400,
"owned_by": "alibaba",
"name": "Qwen-Flash",
"api": {
"types": [
"chat",
"messages"
]
},
"limits": {
"context": 1000000,
"input": 997952,
"output": 32768
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.05,
"output": 0.4,
"cache_read": 0.005,
"cache_write": 0.063
},
"features": [
"structured_output",
"streaming",
"caching"
],
"info": {
"status": "active",
"release_date": "2025-08-01",
"knowledge_cutoff": null,
"description": "Qwen3 Flash combining thinking and non-thinking modes with dynamic switching.",
"docs": "https://www.alibabacloud.com/help/en/model-studio/text-generation-model",
"verified_at": "2026-10-11"
}
}Official sources
4
Text generation models | Alibaba Cloud Model Studiowww.alibabacloud.com2026-10-10Model Studio model pricing | Alibaba Cloudwww.alibabacloud.com2026-10-10Model lifecycle and updates | Alibaba Cloud Model Studiowww.alibabacloud.com2026-10-11Anthropic-compatible Messages API | Alibaba Cloud Model Studiowww.alibabacloud.com2026-10-11