AI BriefingVercel AI Gateway supports MiniMax M3
Key point
Vercel AI Gateway now supports the **MiniMax M3** model, which features a 1-million-token context and multimodal capabilities.
Details
MiniMax M3 model is now available on Vercel AI Gateway. M3 is built on MiniMax Sparse Attention (MSA) and features a 1M-token context window along with native multimodal capabilities.
The model has improved performance in software engineering, terminal-based tool use, and agentic web browsing, and is optimized for multi-turn collaboration. Users can set the model name to minimax/minimax-m3 in the AI SDK to leverage multimodal input that combines text and images.
AI Gateway provides a unified API for calling models and supports the following core features:
- Usage and cost tracking
- Retry, failover, and performance optimization
- Custom reporting and Zero Data Retention support
- Dynamic provider sorting based on latency and cost
AI Gateway passes through provider pricing as-is, without any additional margin or platform fees, and incurs no extra cost even for Bring Your Own Key (BYOK) requests.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.