MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video input with text output, has a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context. That costs roughly 1/20 of the previous generation at 1M tokens, with much faster prefill and decode and the same quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration through an interactive user-simulator framework, it is aimed at sustained, multi-step tasks rather than single-turn execution.
$0.112market price $0.224
$0.0224market price $0.0448
$0.44market price $0.88
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video input with text output, has a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use.
On NagaAI, MiniMax M3 costs $0.112 per 1M input tokens and $0.44 per 1M output tokens. You pay only for what you use, with no subscription.
MiniMax M3 reads up to 1M tokens in one request, counting the prompt and the answer together.
Yes. MiniMax M3 can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.