Question 1

What is the cost of MiniMax M3 Thinking by NanoGPT?

Accepted Answer

MiniMax M3 Thinking by NanoGPT costs $0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached reads cost $0.06 per 1M tokens.

Question 2

What is the context window of MiniMax M3 Thinking by NanoGPT?

Accepted Answer

MiniMax M3 Thinking by NanoGPT has a context window of 512K tokens. It supports up to 512K input tokens and can generate up to 80K output tokens.

Question 3

What are the capabilities of MiniMax M3 Thinking by NanoGPT?

Accepted Answer

MiniMax M3 Thinking by NanoGPT supports advanced reasoning, tool calling/function calling, structured output, adjustable temperature, file attachments. It has open weights.

Question 4

What input and output types does MiniMax M3 Thinking support?

Accepted Answer

MiniMax M3 Thinking by NanoGPT accepts text, image as input and can generate text as output.

Question 5

Does MiniMax M3 Thinking by NanoGPT support reasoning?

Accepted Answer

Yes, MiniMax M3 Thinking by NanoGPT supports advanced reasoning capabilities.

Question 6

Is MiniMax M3 Thinking by NanoGPT open source?

Accepted Answer

Yes, MiniMax M3 Thinking by NanoGPT has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 7

Does MiniMax M3 Thinking support function calling?

Accepted Answer

Yes, MiniMax M3 Thinking by NanoGPT supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

MiniMax M3 Thinking API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)

MiniMax M3 Thinking API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)