Ling 3.1 Flash 1019 free on Vercel AI Gateway until November 3, 2026

Vercel AI Gateway now offers InclusionAI's updated Ling 3.1 Flash 1019, free until November 3, 2026. Free requests still show up in your spend dashboard with a full request trace; they just cost nothing. Starting November 3, requests are billed at the published rate.

What the model is good at

Ling 3.1 Flash 1019 is an updated version of Ling 3.1 Flash, built for coding, multi-step reasoning, and agents that use tools. It is a mixture-of-experts model with about 560B total parameters and about 25B active per token. The context window grows from 262K tokens on the original to 1M tokens, with up to about 262K output tokens, so long documents, large codebases, and long task histories fit in one request.

How to use it

1. Sign in to Vercel and create an API key in AI Gateway.
2. Set the model to inclusionai/ling-3.1-flash-1019.

import { streamText } from 'ai';

const result = streamText({
  model: 'inclusionai/ling-3.1-flash-1019',
  prompt: 'Suggest three ways to make an AI agent more reliable.',
});

For OpenAI-compatible clients, set the base URL to https://ai-gateway.vercel.sh/v1 and use your AI Gateway API key with the same model name.

To use it in Claude Code, Codex, Cursor, and similar tools, install the latest Vercel CLI, run npx vercel ai-gateway setup, then pick inclusionai/ling-3.1-flash-1019 in the agent. You can also try it in Vercel's model playground without writing code.

Another free option

Kilo Code also lists a free version, inclusionai/ling-3.1-flash-1019-free, provided by Novita AI and free until November 3, 2026.

Vercel changelog Vercel model page Kilo Code model list