Back to all models

MiniMax M3

MiniMax M3 is a multimodal foundation model with 512K token context, native multimodal understanding, and MiniMax Sparse Attention (MSA) for efficient long-context inference.

minimax-m3
STABLE
1,000,000 context
Starting at $0.30/M input tokens
Starting at $1.20/M output tokens
Streaming
Vision
Tools
Reasoning
JSON Output

Select Provider

All Providers for MiniMax M3

LangRouter routes requests to the best providers that are able to handle your prompt size and parameters.

LangRouter

langrouter/minimax-m3
Context Size
1M
Stability
STABLE
Pricing
Input
$0.3000
/M
Cached
$0.0600
/M
Output
$1.2000
/M
Capabilities
Streaming
Vision
Tools
Reasoning
JSON Output
Try in Playground