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

CapabilitySupportCapabilitySupport
Input ModalityTextOutput ModalityText
Model ExperienceUnsupportedFunction CallingSupported
Structured OutputsSupportedWeb SearchUnsupported
Prefix CompletionSupportedContext CachingSupported
Batch InferenceUnsupportedFine-tuningUnsupported

Context Limits

ParameterValueParameterValue
Max Input Length1048576Max Output Length262144
Context Window1048576Max Input Length (Thinking Mode)1048576
Max Output Length (Thinking Mode)262144Max Chain-of-Thought Length262144

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 ItemPrice (CNY)Unit
Input2Per 1M tokens
Output6Per 1M tokens
Input (Cache Hit)0.4Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue
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.