7 providersLlama 4 Scout 17B 16E InstructCurrently listed through these providers:AzureAzure Cognitive ServicesCloudflare AI GatewayCloudflare Workers AIGitHub Models+2 more
7 providersLlama 4 Maverick 17B 128E Instruct FP8Currently listed through these providers:AbacusAzureAzure Cognitive ServicesGitHub ModelsLlama+2 more
5 providersLlama 3.3 70B InstructCurrently listed through these providers:Berget.AINanoGPTNovitaAIRegolo AIVertex
4 providersLlama 3.1 8B InstructCurrently listed through these providers:Cloudflare AI GatewayInferenceNvidiaRegolo AI
3 providersLlama 4 Maverick 17B 128E InstructCurrently listed through these providers:DigitalOceanIO.NETVertex
3 providersLlama Guard 3 8BCurrently listed through these providers:Cloudflare AI GatewayCloudflare Workers AIOpenRouter
2 providersLlama 4 Maverick 17B InstructCurrently listed through these providers:Amazon BedrockLLM Gateway
2 providersLlama 4 Scout 17B InstructCurrently listed through these providers:Amazon BedrockLLM Gateway
May 30, 2026, 12:41 PMUTCEntire world: We need more GPUs Meanwhile, Jensen Huang: VideoOpen post on X
Jun 1, 2026, 1:59 AMUTCIntroducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to…Open post on X
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.