MiniMax M3 is a multimodal foundation model with 512K token context, native multimodal understanding, and MiniMax Sparse Attention (MSA) for efficient long-context inference.
PassingRight 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 PassingRight's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for MiniMax M3 on PassingRight starts at $0.30 per million input tokens and $1.20 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 1,000,000 tokens on its largest provider deployment.
MiniMax M3 is served by Together AI, MiniMax, Tencent Cloud through PassingRight. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. MiniMax M3 supports both tool (function) calling and strict JSON output schema (upstream-enforced) through PassingRight.
MiniMax M3 was released on June 1, 2026.
MiniMax H3 Max
7,000 context$0.00 in / $0.00 out per 1M
MiniMax M2.7
204,800 context$0.08 in / $0.32 out per 1M
MiniMax M2.7 Highspeed
204,800 context$0.60 in / $2.40 out per 1M
MiniMax M2.5
204,800 context$0.30 in / $1.20 out per 1M
MiniMax M2.5 Highspeed
204,800 context$0.60 in / $2.40 out per 1M
MiniMax M2.1
204,800 context$0.27 in / $1.10 out per 1M