MiniMax M3.1 Flash is free on Vercel AI Gateway until October 20. The open-weight multimodal model carries a 1 million token context window and targets coding, agentic workflows, and cybersecurity tasks. To guarantee the free rate, pin MiniMax as the provider using the order field in provider options. After the 20th, standard MiniMax billing applies.
The model's documented strengths are multi-step business process automation, cross-application computer use, frontend development, targeted bug fixes, and component testing. It is callable via the AI SDK, OpenAI Chat Completions, Responses, and Anthropic Messages APIs, or through a coding agent connected to AI Gateway. The model identifier is minimax/minimax-m3.1-flash. Claude Code, Codex, and Cursor support is available through the latest Vercel CLI.
The full article is worth reading for the provider pinning mechanic: if you skip that configuration step, requests may not route through MiniMax and you lose the free pricing. It also details how AI Gateway handles failover, routing rules, Zero Data Retention, and per-key budget controls, all with no platform markup on inference, including BYOK requests.
[READ ORIGINAL →]