NVIDIA Launches Free GPU-Accelerated Endpoint for MiniMax M3 Multimodal Model

NVIDIA

Jun 13, 2026

NVIDIA now provides a free GPU-accelerated endpoint for MiniMax M3, a 428B parameter Mixture-of-Experts model. Developers can use the endpoint to test the model's 1-million-token context window and native multimodal reasoning for text, image, and video tasks. The model is available for prototyping and evaluation on the NVIDIA build platform.

MINIMAX | NVIDIA — Minimax and NVIDIA partnership announcement highlighting collaborative efforts in AI computing and developer platform infrastructure development.

View the full update on developer.nvidia.com

NVIDIA AI

@NVIDIAAI1d ago

Congrats to the @MiniMax_AI team on the release of MiniMax M3, a long-context multimodal model for text, image, and video reasoning. 🙌 Try it today with our free GPU-accelerated endpoint on https://t.co/es07MrU5I0. Details: https://t.co/89qlcTP3OW https://t.co/iyMhbW03nQ

1121.3k

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Keep reading

MiniMax brings M3 to local PCs with 1M context open weights

MiniMax announced that its M3 model is joining the NVIDIA and Microsoft local LLM lineup, with weights releasing to the community within 10 days. The move brings high-capacity multimodal reasoning and coding capabilities directly to local hardware.

Fireworks AI Adds Day-0 Support for MiniMax M3 Multimodal Model

Fireworks AI15h ago

Fireworks AI Adds Day-0 Support for MiniMax M3 Multimodal Model

Fireworks AI launched day-0 support for MiniMax M3, a multimodal model featuring native image and video input. Powered by MiniMax Sparse Attention, the model delivers 9× faster prefill and 15× faster decode speeds. It is available now on serverless and on-demand endpoints, priced at parity with M2.7 at $0.30 per million input tokens.

NVIDIAApr 29

NVIDIA Launches Nemotron 3 Nano Omni for Efficient Multimodal Sub-Agents

NVIDIA released Nemotron 3 Nano Omni, a 30B-parameter multimodal model that unifies text, image, video, and audio understanding into a single architecture. By activating only 3 billion parameters during inference, the model delivers high-efficiency reasoning across a 256K context window for complex agentic workflows.

Arena adds MiniMax M3 for community testing of 1M context model

ArenaJun 1

Arena adds MiniMax M3 for community testing of 1M context model

Arena.ai added MiniMax M3 to its evaluation platform, allowing users to test the new open-weights model across text, vision, and coding tasks. The model features a 1-million-token context window and achieved a 59.0% score on the SWE-Bench Pro benchmark.