Skip to content
ShilpBot
AI Models

MiniMax M3.1 Flash: Pricing, Specs and Limits

MiniMax M3.1 Flash: multimodal model with gains in agentic tasks, coding and cybersecurity, 1M context, 0.15 in / 0.60 out per 1M tokens. Specs, limits...

By ShilpBot Team · Published · 3 min read

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, the listing says it improves significantly across multiple benchmarks, particularly in complex agentic tasks, coding and cybersecurity.

It is priced at $0.15 per million input tokens and $0.60 per million output tokens, with cached input at $0.015, so repeated large prompts cost very little.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

MiniMax M3.1 Flash quick facts

DetailValue
DeveloperMiniMax
Model IDminimax/minimax-m3.1-flash
Added to the catalogue2026-10-19
TypeMultimodal model with gains in agentic tasks, coding and cybersecurity
ParametersNot listed
Context windowabout 1M tokens (1,048,576)
Maximum output524,288 tokens
Input typestext, image, video
Price0.15 in / 0.60 out per 1M tokens (cached input 0.015)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What MiniMax M3.1 Flash is good for

  • Cost-efficient agentic and coding work.
  • Security-related analysis, which the listing mentions, such as reading logs or reviewing code for weaknesses.
  • Image and video input at low cost.

Limits of MiniMax M3.1 Flash

  • Use security analysis only on systems you are authorised to test.
  • Benchmark claims come from the provider. Check them on your own tasks.
  • Video input uses many tokens.

How MiniMax M3.1 Flash compares

  • DeepSeek V4.1 Flash 1017: Both have a 1,048,576-token context window; its output cap is 524,288 tokens against 393,216; it also accepts video input; it costs 0.15 input and 0.60 output per million tokens against 0.15 and 0.60.
  • MoonshotAI Kimi K3.1 Pro: Both have a 1,048,576-token context window; its output cap is 524,288 tokens against 943,718; it costs 0.15 input and 0.60 output per million tokens against 0.24 and 8.40.
  • OpenAI GPT-6 Luna: It has a smaller context window (1,048,576 against 1,050,000 tokens); its output cap is 524,288 tokens against 128,000; it also accepts video input; it does not accept file input; it costs 0.15 input and 0.60 output per million tokens against 0.10 and 0.50.

Calling MiniMax M3.1 Flash from code

Use the model ID minimax/minimax-m3.1-flash with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "minimax/minimax-m3.1-flash", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what MiniMax M3.1 Flash can do

  1. Give it a small code sample with a known vulnerability and ask for the issue and a fix.
  2. Run a 10-step tool-using task and count failures.
  3. Compare with DeepSeek V4.1 Flash on the same coding task.

What MiniMax M3.1 Flash costs

The catalogue lists 0.15 per million input tokens and 0.60 per million output tokens, with cached input at 0.015 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.21. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.028 before caching. If your client reuses the same prompt prefix, cached input at 0.015 per million tokens can cut the input side of that bill by about 90 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

What improved in M3.1 Flash over M3?

The listing cites improvements in complex agentic tasks, coding and cybersecurity, based on the provider's benchmarks.

What are the cost and limits of MiniMax M3.1 Flash?

As of 2026-11-16 the catalogue lists 0.15 per million input tokens and 0.60 per million output tokens. About 1M tokens (1,048,576) context window, up to 524,288 output tokens, model ID minimax/minimax-m3.1-flash. Prices can change, so check the live model page.

#MiniMax M3.1 Flash#MiniMax model#AI model pricing#AI API pricing#AI chat model#agentic model#OpenRouter