inclusionAI: Ling 3.0 Tiny

Ling 3.0 Tiny is a text-only model from inclusionAI. It accepts a context window of 262,144 tokens and can return up to 250,000 tokens in a single completion, which suits long documents and lengthy generated outputs. It supports tool calling and a reasoning mode. The available information does not confirm structured output support or whether the weights are open, so verify both before building around them. The main reason to shortlist this model is cost. At $0.015 per million input tokens and $0.045 per million output tokens, it fits high-volume pipelines, agent loops with many tool calls, and long-context batch jobs where per-token spend drives the decision. Quality is unproven, since it has no independent benchmark coverage yet. Teams considering Ling 3.0 Tiny should run their own evaluations on representative tasks and compare results against better-documented models before committing production workloads.