All labs

MiniMax API

MiniMax models from MiniMax, through one OpenAI-compatible API.

MiniMax builds long-context language models and speech and video models. Use them through UltraGPT with one key and one balance.

Models

2

From / 1M input

$0.15

MiniMax M3.1 Flash

Largest context

1.0M

MiniMax M3.1 Flash

MiniMax models and prices

Chat and embedding prices are USD per 1M tokens: input / output.

ModelTypePrice
MiniMax M3.1 Flashminimax-m3.1-flashChat$0.15 / $0.6
MiniMax Speechminimax-speechText to speech$0.1000 / 1K chars

Call MiniMax M3.1 Flash in a few lines

Swap the model id for any model in the table above; nothing else changes.

curl https://api.ultragpt.pro/v1/chat/completions \
  -H "Authorization: Bearer $ULTRAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3.1-flash",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Comparisons

FAQ

How do I get a MiniMax API key?

Sign in to UltraGPT Developers, top up your balance and create an API key. The same key works for every MiniMax model and every other model on UltraGPT - no separate MiniMax account needed.

How much does the MiniMax API cost on UltraGPT?

Chat models of MiniMax start at $0.15 per 1M input tokens (MiniMax M3.1 Flash). You pay per token from a prepaid balance, with no subscription; each model's page lists its exact input, cached-input and output prices.

Does it work with the official SDK?

UltraGPT is OpenAI-compatible: use the official OpenAI SDK (Python, Node.js) or any OpenAI-compatible tool with the base URL https://api.ultragpt.pro/v1 and the model id from the table.

Which MiniMax model has the largest context window?

MiniMax M3.1 Flash (minimax-m3.1-flash), with 1,048,576 tokens.

Quickstart → Use it in Cursor, Claude Code, Cline… → All models →