MiniMax · MultimodalReleased 2026-07-30

minimax-h3

minimax/minimax-h3 id

H3 is a next-generation open-weights, general-purpose multimodal video model. Rather than being limited to specialized tasks such as generating, editing, or referencing, H3 understands multimodal contexts that bring together text, images, video, and audio. This enables it to interpret creative intent in a unified way and deliver more natural, coherent generation and expression.

Chat

Type

Use minimax-h3

# Drop-in OpenAI-compatible client
$ import { generateText } from 'ai'
$ 
$ const { text } = await generateText({
$   model: 'minimax/minimax-h3',
$   baseURL: 'https://synapse.garden/api/v1',
$   apiKey: process.env.MG_KEY,
$   prompt: 'Why is the sky blue?',
$ })

—

CONTEXT WINDOW

—

MAX OUTPUT

—

INPUT · PER M

—

OUTPUT · PER M

PRICING

List prices, every modality.

Rate	Per million tokens · USD
Input	—
Output	—

Honest list pricesHow we calculate prices

Other MiniMax models

See all 9

Model

Input

Output

Context

Type

minimax-m3MiniMax-M3 is a frontier-class foundation model that unites the three capabilities defining today's frontier: a 1M-token context window, frontier coding and agentic performance, and native multimodality — the first open-weight model to deliver all three in a single system.REASONINGTOOLS
Input
$0.330/M
Output
$1.32/M
Context
1M
minimax-m2.7M2.7 delivers outstanding performance in real-world software engineering, including end-to-end full project delivery, log analysis and bug troubleshooting, code security, machine learning, and more.TOOLSREASONING
Input
$0.330/M
Output
$1.32/M
Context
204.8K
minimax-m2.7-highspeedM2.7 Highspeed: Same performance, faster and more agile (output speed approximately 100 tps)REASONINGTOOLS
Input
$0.660/M
Output
$2.64/M
Context
204.8K
minimax-m2.5MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. It is capable of handling the entire development process of various complex systems. It covers full-stack projects across multiple platforms including Web, Android, iOS, Windows, and Mac, encompassing server-side APIs, functional logic, and databases.REASONINGTOOLSLONG-CTX
Input
$0.330/M
Output
$1.32/M
Context
204.8K
minimax-m2.5-highspeedM2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)REASONINGTOOLS
Input
$0.660/M
Output
$2.64/M
Context
204.8K
minimax-m2.1MiniMax 2.1 is MiniMax's latest model, optimized specifically for robustness in coding, tool use, instruction following, and long-horizon planning.REASONINGTOOLS
Input
$0.330/M
Output
$1.32/M
Context
204.8K
minimax-m2.1-lightningMiniMax-M2.1-lightning is a faster version of MiniMax-M2.1, offering the same performance but with significantly higher throughput (output speed ~100 TPS, MiniMax-M2 output speed ~60 TPS).REASONINGTOOLS
Input
$0.330/M
Output
$2.64/M
Context
204.8K
minimax-m2MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence.REASONINGTOOLS
Input
$0.330/M
Output
$1.32/M
Context
205K

FAQ · MINIMAX-H3

Frequently asked

01 / 04

How do I call minimax-h3 from my code?

Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘minimax/minimax-h3’ and supply your Synapse Garden API key. No code changes beyond the base URL.

02 / 04

How much does minimax-h3 cost?

Pricing varies by usage type — see the table above for the current rates.

03 / 04

What's the context window for minimax-h3?

Context window varies — check the live spec sheet at the top of this page.

04 / 04

Do I need a separate Anthropic or OpenAI account?

No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.

READY

Try minimax-h3 in three minutes.

Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.

Start free Quickstart