Based on Qwen3, this code generation model inherits the coding agent capabilities of Qwen3-Coder-Plus and supports multi-turn tool interaction. It features focused optimizations on repository-level understanding and enhanced tool-calling stability. This model version is functionally equivalent to the snapshot model qwen3-coder-flash-2025-07-28.
Inference Service Provider
The inference service provider for qwen3-coder-flash is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 997952 | Max Output Length | 65536 |
Context Window | 1000000 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
Input<=32k
Input<=32k
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.144 | Per 1M tokens |
Output | 0.574 | Per 1M tokens |
Input(Implicit Cache) | 0.029 | Per 1M tokens |
Explicit Cache Creation | 0.18 | Per 1M tokens |
Explicit Cache Read | 0.014 | Per 1M tokens |
32k<Input<=128k
32k<Input<=128k
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.216 | Per 1M tokens |
Output | 0.861 | Per 1M tokens |
Input(Implicit Cache) | 0.044 | Per 1M tokens |
Explicit Cache Creation | 0.27 | Per 1M tokens |
Explicit Cache Read | 0.022 | Per 1M tokens |
128k<Input<=256k
128k<Input<=256k
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.359 | Per 1M tokens |
Output | 1.434 | Per 1M tokens |
Input(Implicit Cache) | 0.072 | Per 1M tokens |
Explicit Cache Creation | 0.449 | Per 1M tokens |
Explicit Cache Read | 0.036 | Per 1M tokens |
256k<Input<=1m
256k<Input<=1m
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.717 | Per 1M tokens |
Output | 3.584 | Per 1M tokens |
Input(Implicit Cache) | 0.144 | Per 1M tokens |
Explicit Cache Creation | 0.896 | Per 1M tokens |
Explicit Cache Read | 0.072 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 5000 |
TPM (Tokens Per Minute) | 5,000,000 |
Snapshot Versions
qwen3-coder-flash-2025-07-28
Based on Qwen3, this code generation model inherits the coding agent capabilities of Qwen3-Coder-Plus and supports multi-turn tool interaction. It features focused optimizations on repository-level understanding and enhanced tool-calling stability. This version is a snapshot dated July 28, 2025.
Inference Service Provider
The inference service provider for qwen3-coder-flash-2025-07-28 is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 997952 | Max Output Length | 65536 |
Context Window | 1000000 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
Input<=32k
Input<=32k
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.144 | Per 1M tokens |
Output | 0.574 | Per 1M tokens |
32k<Input<=128k
32k<Input<=128k
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.216 | Per 1M tokens |
Output | 0.861 | Per 1M tokens |
128k<Input<=256k
128k<Input<=256k
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.359 | Per 1M tokens |
Output | 1.434 | Per 1M tokens |
256k<Input<=1m
256k<Input<=1m
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.717 | Per 1M tokens |
Output | 3.584 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 1,000,000 |