MiniMax M3 on AI Gateway
MiniMax M3 now runs on Vercel AI Gateway. 1M context, native multimodal, sparse attention—available today across SDKs.
Why it matters
MiniMax M3's availability on Vercel AI Gateway expands model choice for developers building with multimodal and agentic workflows. The integration highlights competitive pressure to offer unified API access, cost transparency, and performance optimization tooling across model providers.
The key facts
15 to knowMiniMax M3 features 1M-token context window
Native multimodality support
MiniMax Sparse Attention (MSA) architecture
Optimized for software engineering, terminal tool use, agentic web browsing
Tuned for multi-turn collaboration
Available via Vercel AI Gateway with unified API
AI Gateway offers zero data retention, dynamic provider sorting, bring-your-own-key (BYOK), custom reporting
No platform markup or inference fees on AI Gateway
MiniMax M3 now available on Vercel AI Gateway
1M-token context window
Native multimodal support
Improvements in software engineering, terminal-based tool use, agentic web browsing
AI Gateway offers unified API, usage tracking, cost tracking, retries, failover, performance optimization
No markup on provider pricing, zero platform fees on inference
Bring Your Own Key (BYOK) support included
Go to the source
Vercel Blogvercel.com
Publisher excerpt: MiniMax M3 is now available on .Vercel AI Gateway M3 is MiniMax's first model with a 1M-token context window and native multimodality, built around MiniMax Sparse Attention (MSA). M3 improves on software engineering, terminal-based tool use, and agentic web browsing, and is tuned for multi-turn…