MiniMax M3.1 Flash Free on Vercel AI Gateway Until Oct 20

What the model offers

According to Vercel, MiniMax M3.1 Flash is an open-weight multimodal model built for coding and agentic work. Its 1M-token context window is meant for long documents and multi-step agent sessions.

Vercel says that compared with earlier MiniMax models, M3.1 Flash improves on complex agentic tasks, coding and cybersecurity. On the agent side, that covers multi-step business processes and computer use that carries a task from one application to the next.

For coding, MiniMax reports its best results on application development, particularly frontend interactions, targeted bug fixes and component tests. These are the company's own claims, and the source gives no benchmark figures.

How the free offer works

The free rate runs until Oct 20 and applies only when MiniMax itself serves the request. To make sure that happens, developers need to sort the provider with order in the gateway provider options. After the offer ends, pinned requests bill at MiniMax's standard rate.

The model can be called through the AI SDK, as well as the Chat Completions, Responses and Anthropic Messages APIs. A coding agent connected to AI Gateway also works. The model name is minimax/minimax-m3.1-flash.

Vercel's example uses the AI SDK's streamText function with the reasoning setting at 'low', and asks the model to write a SQL query that finds duplicate emails in a users table.

Using it in coding agents

To use the model in Claude Code, Codex, Cursor and other agents, Vercel says to install the latest Vercel CLI and run npx vercel ai-gateway setup. After that, users select minimax/minimax-m3.1-flash in the agent. Vercel also points to a coding agents guide and a model playground for trying the model.

About AI Gateway and what it means for developers

AI Gateway offers a unified API for calling models, tracking usage and cost, and configuring retries, failover and performance optimizations for higher-than-provider uptime. Vercel lists built-in custom reporting, Zero Data Retention support, budgets for API keys and routing rules among its features.

The company states that AI Gateway reflects provider pricing with no markup and charges no platform fee on inference, including on Bring Your Own Key (BYOK) requests.

For developers, the offer was a time-limited chance to test an open-weight model with a long context window on coding and agent workloads without paying for inference, provided requests were pinned to MiniMax. Anyone who keeps using it after the window closes pays MiniMax's standard rate.