All Models

Ling 3.0 Flash

lingReasoningTool CallingOpen Weights

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

Providers4
ReleasedJul 23, 2026
Input Modalitiestext
Output Modalitiestext
Tarsk Usecoding

Benchmarks

20.6
Intelligence Index
50.6
Coding Index

Available Providers (4)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Vercel AI Gatewayinclusionai/ling-3.0-flash$0.02/MTok$0.06/MTok256K32K
OpenRouterinclusionai/ling-3.0-flash$0.02/MTok$0.06/MTok262.1K32.8K
Kilo Gatewayinclusionai/ling-3.0-flash$0.06/MTok$0.18/MTok262.1K32.8K
NanoGPTinclusionai/ling-3.0-flash$0.07/MTok$0.22/MTok262.1K32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output