MiniMax M3.1 Flash now available in AI Gateway and Agent Runners
By Steven Van ·
Netlify's AI Gateway needs no API keys for the model, which also runs in Scheduled, Background and Edge Functions through the OpenRouter SDK.
MiniMax M3.1 Flash can now be used through Netlify's AI Gateway and Agent Runners, according to the changelog. No configuration is required.
Calling the model from a function
The OpenRouter SDK works directly inside Netlify Functions, with no API keys or authentication to manage. AI Gateway handles both automatically. In the vendor's example, a function creates an OpenRouter client, calls client.chat.send with the model set to minimax/minimax-m3.1-flash, passes a user message and a maxTokens of 400, and returns the response as JSON.
Where it runs
The model is also available in Scheduled Functions, Background Functions and Edge Functions. In each, Netlify's caching, rate limiting and authentication infrastructure applies automatically.
The announcement links to the AI Gateway and Agent Runners documentation for details.
