Minimax H3

Name: Minimax H3
Author: Together AI

deprecatedproprietary

Next-generation open, general-purpose multimodal video model supporting text-to-video, image-to-video, first-and-last-frame generation, and multimodal references. Supports 768P / 2K output and videos from 4 to 15 seconds

Input price

$0.14/1M tokens

Output price

$0.14/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDs/minimax-h3

ProviderTogether AI

CreatorMiniMax

Familyminimax

Licenseproprietary

Parameters—

Statusdeprecated

Input modalitiestext

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date—

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weightNo

Sourceofficial

Last updated2026-11-11

Pricing

Input

$0.14

↓18%$0.17

Output

$0.14

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Price history · $/1M input

$0.17

$0.14

$0.17

$0.139

Sep 15Sep 18Oct 6Nov 11

Date	Input	Output	Change
Sep 15, 2026	$0.17	$0.139	—
Sep 18, 20262ae168f	$0.14	$0.139	↓18%
Oct 6, 202600710a0	$0.17	$0.139	↑21%
Nov 11, 20262a8a794	$0.139	$0.139	↓18%

Input is ↓18% since Sep 15, 2026, from $0.17 to $0.139 per 1M tokens.

Family Comparison: minimax

Model	Caps	Perf	Speed	Context	Max out	Pricing
Minimax Speech 2 6 Turbo	RVTS	—	—	—	—
Minimax Speech 28	RVTS	—	—	—	—
Minimax M3 1 Flash	RVTS	—	—	—	—	$0.02$0.6
Minimax M2 5	RVTS	—	—	192K	—	$0.06$1.2
Minimax M2 7	RVTS	—	—	—	—	$0.06$1.2
Minimax M3	RVTS	—	—	1M	—	$0.06$1.2
Minimax H3	RVS	—	—	—	—	$0.14$0.14

API

GET/v1/models/together/s/minimax-h3