MiniMax M3 is a multimodal foundation model with 512K token context, native multimodal understanding, and MiniMax Sparse Attention (MSA) for efficient long-context inference.
DigitSpace routes requests to the best providers that are able to handle your prompt size and parameters.
MiniMax M3 is a multimodal foundation model with 512K token context, native multimodal understanding, and MiniMax Sparse Attention (MSA) for efficient long-context inference. You can access it through DigitSpace's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for MiniMax M3 on DigitSpace starts at $0.39 per million input tokens and $1.57 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
MiniMax M3 supports a context window of up to 128,000 tokens on its largest provider deployment.
MiniMax M3 is served by MiniMax through DigitSpace. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
MiniMax M3 supports tool (function) calling, but not JSON output modes.
MiniMax M3 was released on June 1, 2026.