Question 1

What is the cost of MiniMax M2.5 by HPC-AI?

Accepted Answer

MiniMax M2.5 by HPC-AI costs $0.14 per 1M input tokens and $0.56 per 1M output tokens. Cached reads cost $0.01 per 1M tokens.

Question 2

What is the context window of MiniMax M2.5 by HPC-AI?

Accepted Answer

MiniMax M2.5 by HPC-AI has a context window of 1.0M tokens. It supports up to 1.0M input tokens and can generate up to 131K output tokens.

Question 3

What are the capabilities of MiniMax M2.5 by HPC-AI?

Accepted Answer

MiniMax M2.5 by HPC-AI supports advanced reasoning, tool calling/function calling, adjustable temperature. It has open weights.

Question 4

What input and output types does MiniMax M2.5 support?

Accepted Answer

MiniMax M2.5 by HPC-AI accepts text as input and can generate text as output.

Question 5

Does MiniMax M2.5 by HPC-AI support reasoning?

Accepted Answer

Yes, MiniMax M2.5 by HPC-AI supports advanced reasoning capabilities.

Question 6

Is MiniMax M2.5 by HPC-AI open source?

Accepted Answer

Yes, MiniMax M2.5 by HPC-AI has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 7

Does MiniMax M2.5 support function calling?

Accepted Answer

Yes, MiniMax M2.5 by HPC-AI supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

MiniMax M2.5 API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)