# OpenRouter adds free inclusionAI Ling 3.2 Flash model

> The new Ling 3.2 Flash model is now available on OpenRouter with 1.94 s latency, 32 tokens/s throughput and 98.82% availability.

Oossa · 2026-11-13 · https://oossa.com/en/openrouter-adds-free-inclusionai-ling-3-2-flash-model

OpenRouter has added a new free model called inclusionAI: Ling 3.2 Flash. The model runs on a single provider but OpenRouter will automatically switch to another if the first fails. It delivers 32 tokens per second and a round‑trip latency of 1.94 seconds, which is the best among the providers listed. Availability over the past three days is recorded at 98.82 %. The API works with any OpenAI‑compatible SDK by changing the base URL and model slug.

## The facts

- Model name: inclusionAI: Ling 3.2 Flash
- Latency: 1.94 seconds; Throughput: 32 tokens per second; Availability: 98.82 %

## Why it matters

Developers can try a high‑throughput, low‑latency LLM for free without worrying about downtime, speeding up prototyping of chat or text‑generation apps.

## Sources & references

1. [New on OpenRouter: inclusionAI: Ling 3.2 Flash (free)](https://openrouter.ai/inclusionai/ling-3.2-flash:free) – OpenRouter API, 2026-11-13

Last updated: 2026-11-13