MiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.
Modalities
In / out price
$0.30 / $1.20
per 1M
Cached price
$0.06
per 1M
Context
524K
Max output
66K
Released
Jun 12, 2026
Providers
1 routeThe same model can have different pricing and privacy guarantees depending on who serves it. The model's headline privacy uses the strongest available route below. Discovered routes awaiting approval remain listed as not live.
| Provider | Privacy | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output | Uptime | Latency | Throughput |
|---|---|---|---|---|---|---|---|---|---|
| Private | $0.30 | $1.20 | $0.06 | 524K | 66K | — | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
7Streaming
Tool calling
Reasoning
Vision
Web search
Code optimized
Prompt caching