Last refreshed 2026-06-01. Next refresh: weekly.
Why use MiniMax M3 on MiniMax?
MiniMax offers MiniMax M3 with pay-as-you-go pricing at $0.60/1M input tokens. MiniMax is a multimodal foundation model and API platform for text, speech, video, image, and music generation with agent tools.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: MiniMax-M3MiniMax-M3Request example
MiniMax-M3.Gotchas
- Use provider model ID "MiniMax-M3", not the LLMReference slug "minimax-m3".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.60 |
| Output tokens | $2.40 |
| Image input | $1.00 |
| Video input | $1.00 |
Capabilities
About MiniMax M3
MiniMax M3 is a frontier multimodal model released May 31, 2026, accepting text, image, and video inputs with up to 1 million tokens of context. Built on MiniMax Sparse Attention, it targets production coding and long-horizon agent workflows with lower long-context attention cost, 9.7x faster prefill, 15.6x faster decode versus MiniMax M2 at 1M tokens, interleaved reasoning between tool calls, function calling, and automatic prompt caching.
FAQ
What does MiniMax M3 cost on MiniMax?
On MiniMax, MiniMax M3 costs $0.60 per 1M input tokens and $2.40 per 1M output tokens.
What is the context window for MiniMax M3 on MiniMax?
MiniMax M3 supports a 1m token context window on MiniMax.
What API model ID do I use for MiniMax M3 on MiniMax?
Use the model ID MiniMax-M3 when calling MiniMax's API.
Who created MiniMax M3?
MiniMax M3 was created by MiniMax as part of the MiniMax M3 model family.
Is MiniMax M3 open source?
MiniMax M3 is not open source; the seed data lists it as proprietary.