Skip to content
OfferSign up and get $10 of credit for any model in Chat and the API. Top up from $1, with no processing fees. See free models →·Some free models are at the daily cap — refills 05:30 IST; requests auto-route to a live backup. Status →
One AI API Key
Get API key

MiniMax · MiniMax · Balanced

MiniMax M3

Discount −46%New

MiniMax's multimodal model for long agentic work, coding and tool use, with text, image and video input.

Model id

minimax-m3
Get an API keyTry in Chat

Price per 1M tokens

Input
Regular rate $0.30now $0.161
Output
Regular rate $1.20now $0.672
Cached input
$0.0663% below input

46% below the market rate.

Added here 18 Oct 2026 — read the changelog for what changed and why.

Output is 4.2× the input rate. $1 covers about 2,016 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates

Start using MiniMax M3

Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.

curl https://api.oneaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "stream": true,
    "messages": [{"role": "user", "content": "Check the order status for each customer in this list and draft a reply to the late ones."}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oneaiapikey.com/v1",
    api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)

stream = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Check the order status for each customer in this list and draft a reply to the late ones."}],
    stream=True,  # recommended for long outputs
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.oneaiapikey.com/v1",
  apiKey: process.env.ONEAIAPIKEY_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "minimax-m3",
  messages: [{ role: "user", content: "Check the order status for each customer in this list and draft a reply to the late ones." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

More: quickstart · API reference · try it in Chat first

Benchmarks reported by the vendor

Scores for MiniMax M3 as its maker published them, with the setting they state. We have not re-run them. Versions and settings differ between vendors, so compare only identical benchmark names; compare models side by side.

Tokens per day, by model

Last 7 days, UTC days

Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.

Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.

Full ranking insights

Nearest alternative

MiniMax M3 or GLM 5.3?

MiniMax M3 is the only MiniMax model here. GLM 5.3 from Z.ai is the closest-priced balanced-tier model from another vendor. Each comparison lists the published rates and limits, then what favours each side.

MiniMax M3vsGLM 5.3

Per 1M tokensMiniMax M3GLM 5.3
Input$0.16159% less$0.396
Output$0.67213% less$0.77
Cached input$0.0677% less$0.26
Context1M2% smaller1.02M
Max output131.1k2% more128k

Pick MiniMax M3 when

  • cost per request decides it: MiniMax M3 charges input 59% less and output 13% less than GLM 5.3.
  • one answer must be longer than 128k tokens (its limit is 131.1k).
  • you rely on Vision, which GLM 5.3 does not list.
  • requests include screenshots or other images.
  • the work is agentic work, coding and long context, which this catalogue lists for MiniMax M3 and not for GLM 5.3.

Pick GLM 5.3 instead when

  • inputs outgrow the 1M-token window of MiniMax M3; GLM 5.3 accepts 1.02M.
  • your workload looks like coding help, writing and translation, labels the catalogue gives GLM 5.3 only.

Use cases

What MiniMax M3 is listed for, and what it costs

The catalogue lists MiniMax M3 for agentic work, coding and long context. Each row prices one typical request at the published rates, with the arithmetic shown. The market-rate figure shows the same request at the lowest public price elsewhere. Token counts are examples; your prompts will differ.

Model your own traffic

  1. Agentic work

    One step of a tool-using agent: 20,000 tokens of instructions, tool results and history, 15,000 of them cached, and 1,000 tokens of tool calls and notes out.

    “Check the order status for each customer in this list and draft a reply to the late ones.”

    Same request on GLM 5.3 $0.00665.

    $0.002378

    per agent step, about 4,205 per $10

    $0.0036 at the market rate

    0.005 × $0.161 + 0.015 × $0.06 + 0.001 × $0.672

  2. Coding

    Implementing a function or endpoint: 8,000 tokens of context in, 2,000 tokens of code out.

    Capable across languages for implementation, debugging and explaining code.

    “Write a TypeScript endpoint that returns paginated orders for the signed-in user.”

    Same request on GLM 5.3 $0.004708.

    $0.002632

    per task, about 3,799 per $10

    $0.0048 at the market rate

    0.008 × $0.161 + 0.002 × $0.672

  3. Long context

    A whole codebase or report in one prompt: 400,000 tokens in, a 2,000-token answer out.

    Combine large inputs with cached-input pricing to keep repeat reads cheap.

    “Using the whole repository, list every place that reads the session cookie.”

    Same request on GLM 5.3 $0.15994.

    $0.065744

    per request, about 152 per $10

    $0.1224 at the market rate

    0.4 × $0.161 + 0.002 × $0.672

Overview

When MiniMax M3 fits

MiniMax M3 is a balanced model from MiniMax, available here under the exact model id “minimax-m3”. It is currently the only MiniMax model we serve. MiniMax has not published a release date we can cite; it has been available here since 18 Oct 2026.

MiniMax documents tools, vision, reasoning, json mode and prompt caching for it, and it reads images as well as text.

It costs $0.161 per million input tokens and $0.672 per million output tokens, so output is 4.2× the input rate. That is 46% below the market rate of $0.30 input and $1.20 output per million tokens, the lowest public price we found at other API gateways. On the use cases below, output makes up 28% of the bill for agentic work, 51% for coding and 2% for long context, so trimming the context you send saves more than capping the answer. With a 3:1 input-to-output mix it ranks 6th lowest-cost of the 27 models on this site.

Cached input bills at $0.06 per million tokens, 63% below the standard input rate. In the agentic work example, 15k of the 20k input tokens come from cache, which brings one agent step from $0.003892 down to $0.002378.

It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.

Similar models

Same tier, other vendors

Same key, same balance. Switching is a change to the model field.

Compare side by sideAll models

Use MiniMax M3 with any balance.

MiniMax M3 is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.

Create an accountSee pricing

MiniMax M3 is developed by MiniMax. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by MiniMax.