Model · MiniMax

MiniMax M3.1 Flash

minimax/minimax-m3.1-flash

Try in Agents

MiniMax's fast, low-cost M3.1 model with vision support for everyday agent work

reasoningvisioncaching

Specs

Context

1.0M

Max output

1.0M

Provider

MiniMax

Input

$0.150/ 1M tokens

Output

$0.600/ 1M tokens

Cache read

$0.015/ 1M tokens

Providers and pricing

Vercel AI Gateway	List price	Our price
Input	$0.150 / 1M tokens	$0.150 / 1M tokens
Output	$0.600 / 1M tokens	$0.600 / 1M tokens
Cache read	$0.015 / 1M tokens	$0.015 / 1M tokens

List price is what the provider charges us. Our price is what a request is billed.

Live performance

Loading measurements…

How we measure. Every request is timed from the moment we send it. A finish time comes from the provider's own timestamps when it reports them, from the moment it calls us back when it doesn't, and otherwise from polling: we take the midpoint between the last check that found the job running and the first that found it done, so it is off by at most half the poll interval. First token is the wait for the first streamed text or tool token; output speed counts tokens after that first token. Requests you stop are left out. Figures appear once a window has 20 completed requests, and are aggregate only.

Try it

Chat with MiniMax M3.1 FlashTerramind API

⌘+Enter to run

Code

import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("minimax-m3.1-flash"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by MiniMax

Model	Context	In	Out	Capabilities
minimax/minimax-m2.7	205K	$0.300	$1.20	caching
minimax/minimax-m3	512K	$0.300	$1.20	reasoningcaching
minimax/minimax-h3-max	0	$0	$0	image to videoreference imagesnative audio
minimax/minimax-h3-max-turbo	0	$0	$0	image to videonative audiofirst and last frame