antdigital/Ling-3.1-flash
Updated at:
antdigital/Ling-3.1-flash is a Ling model whose inference service is provided by AntDigital. It has about 560B total parameters, activates about 25B parameters per token, and supports a context window of up to 1M. It is suited for tasks such as general-purpose agents, search, everyday office work, and software development. It supports only text input.
Inference Service Provider
The inference service provider for antdigital/Ling-3.1-flash is AntDigital.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
| Input Modality | Text | Output Modality | Text |
| Model Experience | Unsupported | Function Calling | Supported |
| Structured Outputs | Supported | Web Search | Unsupported |
| Prefix Completion | Supported | Context Caching | Supported |
| Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
| Max Input Length | 1048576 | Max Output Length | 262144 |
| Context Window | 1048576 | Max Input Length (Thinking Mode) | 1048576 |
| Max Output Length (Thinking Mode) | 262144 | Max Chain-of-Thought Length | 262144 |
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)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
| Input | 2 | Per 1M tokens |
| Output | 6 | Per 1M tokens |
| Input (Cache Hit) | 0.4 | Per 1M tokens |
Rate Limits
China (Beijing)
| Parameter | Value |
|---|---|
| RPM (Requests Per Minute) | 300 |
| TPM (Tokens Per Minute) | 10,000,000 |
Invocation
Call the model using the OpenAI-compatible API. For instructions, see Ling-AntDigital.
Is this page helpful?