Fireworks AI

Fireworks AI: MiniMax-M3 (Fireworks)

stable

MiniMax-M3 (Fireworks) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

accounts__fireworks__models__minimax-m3minimaxreleased Jun 12, 2026
ProviderQuick start
Context
512K
tokens
Max output
512K
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
NVIDIA NIM
NVIDIA NIM
1M--
Fireworks AI
Fireworks AI
512K$0.30$1.20
Hugging Face
Hugging Face
524.3K$0.30$1.20
MiniMax
MiniMax
1M$0.30$1.20
OpenRouter
OpenRouter
1.0M$0.30$1.20
Together AI
Together AI
524.3K$0.30$1.20

Pricing

ItemPriceUnit
Input$0.30per 1M tokens
Output$1.20per 1M tokens
Cache read$0.060per 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
accounts__fireworks__models__minimax-m3
Family
minimax
Status
stable
Knowledge
-
Released
Jun 12, 2026
Gateway Config
API
2024-01-01
Auth
FIREWORKS_API_KEY
Discovery
static
Provider type
meta

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: "@fireworks/accounts__fireworks__models__minimax-m3",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.fireworks.ai/inference/v1
Chat completions
https://api.fireworks.ai/inference/v1/chat/completions
Model
accounts__fireworks__models__minimax-m3
Auth env
FIREWORKS_API_KEY

MiniMax-M3 (Fireworks) FAQ

How much does the MiniMax-M3 (Fireworks) API cost?

Through Fireworks AI, MiniMax-M3 (Fireworks) costs $0.30 per 1M input tokens and $1.20 per 1M output tokens.

What is the context window of MiniMax-M3 (Fireworks)?

MiniMax-M3 (Fireworks) accepts up to 512K tokens of context and returns up to 512K output tokens on Fireworks AI.

Which providers offer MiniMax-M3 (Fireworks)?

MiniMax-M3 (Fireworks) is available from NVIDIA NIM, Fireworks AI, Hugging Face, MiniMax, OpenRouter and Together AI. Everstack can route between them with automatic fallback when one is unavailable.

What can MiniMax-M3 (Fireworks) do?

MiniMax-M3 (Fireworks) supports chat, function calling, image input and reasoning. It accepts text, image and video input.

How do I call MiniMax-M3 (Fireworks) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @fireworks/accounts__fireworks__models__minimax-m3. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.