MiniMax

MiniMax: MiniMax M2

stable

MiniMax M2 is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

MiniMax-M2minimax-m2released Oct 27, 2025
ProviderQuick start
Context
196.6K
tokens
Max output
128K
tokens
Input
$0.30
per 1M
Output
$1.20
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
MiniMax
MiniMax
196.6K$0.30$1.20

Pricing

ItemPriceUnit
Input$0.30per 1M tokens
Output$1.20per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
MiniMax-M2
Family
minimax-m2
Status
stable
Knowledge
-
Released
Oct 27, 2025
Gateway Config
API
v1
Auth
MINIMAX_API_KEY
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@minimax/MiniMax-M2",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.minimax.io/v1
Chat completions
https://api.minimax.io/v1/chat/completions
Model
MiniMax-M2
Auth env
MINIMAX_API_KEY

MiniMax M2 FAQ

How much does the MiniMax M2 API cost?

Through MiniMax, MiniMax M2 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens.

What is the context window of MiniMax M2?

MiniMax M2 accepts up to 196.6K tokens of context and returns up to 128K output tokens on MiniMax.

What can MiniMax M2 do?

MiniMax M2 supports chat, function calling and reasoning. It accepts text input.

How do I call MiniMax M2 through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @minimax/MiniMax-M2. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.