Ling 3.0 Flash Thinking

ling Reasoning Tool Calling

Ling-3.0-flash Thinking enables visible reasoning on inclusionAI's token-efficient 124B-parameter Mixture-of-Experts model for harder coding, tool use, planning, and production-scale agent workflows.

Providers 1

Released Jul 23, 2026

Input Modalities text

Output Modalities text

Tarsk Use coding

Available Providers (1)

Provider	Model ID	Input Cost	Output Cost	Context	Max Output	Docs
NanoGPT	`inclusionai/ling-3.0-flash:thinking`	$0.06/MTok	$0.18/MTok	262.1K	32.8K

Capabilities

Reasoning

Tool Calling

Attachments

Open Weights

Structured Output