Source: vercel.com/changelog/minimax-m3-1-flash-now-available-on-ai-gateway-for-free
MiniMax M3.1 Flash is an open-weight multimodal model with a 1M-token context window for long documents and multi-step agent sessions. MiniMax says it improves on earlier models for complex agentic tasks, coding and cybersecurity, including multi-step business processes and computer use that moves a task from one application to the next.
The free rate applies only when MiniMax serves the request, so developers need to sort the provider with order in the gateway provider options to ensure that. Once the offer ends, pinned requests are billed at MiniMax's standard rate.
The model can be called through the AI SDK, the Chat Completions, Responses and Anthropic Messages APIs, or from a coding agent connected to AI Gateway, using minimax/minimax-m3.1-flash as the model name. For tools such as Claude Code, Codex and Cursor, Vercel says to install the latest Vercel CLI and run npx vercel ai-gateway setup.
Why it matters if you build agents
Agent builders can test MiniMax M3.1 Flash on coding and computer-use workloads at no charge until Oct 20. To get the free rate, pin the provider order in the request, because the offer does not apply when another provider serves it.
After Oct 20, pinned requests move to MiniMax's standard pricing, so cost estimates for agents using this model should be updated before then.
Get stories like this every weekday
One short email with the day's agent tooling news.