MiniMax M3.1 Flash API: pricing and how to use it

MiniMax M3.1 Flash (minimax-m3.1-flash), which MiniMax released on October 19, 2026, is now available on FastMetal through the API and in chat. It is built for agentic work, coding and computer use, and it costs about half as much as MiniMax M3.

What MiniMax claims

• Speed. Inference roughly three times faster than its predecessor, with output above 200 tokens per second and a median above 170. MiniMax puts the cost of agentic tasks 70% lower.
• Agent and coding scores. 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, 76.2 on BankerToolBench.
• Space Bunny. The anonymous model that processed more than 200 trillion tokens before launch was an early version of M3.1 Flash.

MiniMax says the weights will be released later.

What we verified

• Image input works. We checked it on a real image before launch.
• Tool calling works, including a forced tool_choice.
• 1M-token context. Served at 1,048,576 tokens.
• Not supported here: PDF input, and strict json_schema output. On our host the model returned prose instead of the schema on 3 of 3 attempts, so we do not advertise it.
• It reasons before answering, and reasoning tokens bill as output.

Pricing

$0.1583 per 1M input tokens and $0.633 per 1M output tokens, with cached input at $0.0158 per 1M. That is roughly half of MiniMax M3 on both meters. Billing is prepaid, so you can never spend more than you have loaded. Exact current rates are on the model page and pricing.

The host has not published a training policy for prompts, so the model page lists training use as unknown.

Calling it

FastMetal's API is OpenAI-compatible. An example with a tool:

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Authorization: Bearer $FASTMETAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3.1-flash",
    "messages": [{"role": "user", "content": "What is the weather in Osaka right now?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city",
        "parameters": {
          "type": "object",
          "properties": {"city": {"type": "string"}},
          "required": ["city"]
        }
      }
    }]
  }'

It thinks at length on hard problems. On one of our coding prompts it produced about 15,000 tokens, reasoning included, and took over two minutes to finish. On the API, stream the response ("stream": true). If you leave out max_tokens, FastMetal allows up to 32,768 output tokens on this model.

In our tests its Japanese answers occasionally carried stray words from other languages, and once its working notes leaked into the final answer. Check the output before you ship it.

To try it without code, pick MiniMax M3.1 Flash in chat. You can attach an image there.

Compare real answers first

The model page shows MiniMax M3.1 Flash's actual answers to our 43 shared prompts: summarization, bug fixing, translation and more. Check them against MiniMax M3 and the models you already use.

Browse the full model catalog.