AI TOOLS RADAR
All models / MINIMAX
minimax logo
minimax

MiniMax: MiniMax M3

Source description (English)

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
512,000 tokens
Architecture
text+image+video->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.3
per 1M tokens
Output
$1.2
per 1M tokens
Cache read
$0.06
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Reasoning required
No
Default parameters
No
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/minimax-m3","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideo
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

12 providers

Checked: September 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

CoreWeave

fp4
Context
262K
Maximum output
236K
Input
$0.23
Output
$0.96
Cache read
$0.05
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.24
Output
$0.96
Cache read
$0.048
Cache write
Not provided

DeepInfra

fp8
Context
524K
Maximum output
512K
Input
$0.28
Output
$1.1
Cache read
$0.056
Cache write
Not provided

StreamLake

fp8
Context
1M
Maximum output
512K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

Venice

fp8
Context
524K
Maximum output
66K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

Together

Not provided
Context
524K
Maximum output
472K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
524K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

AtlasCloud

fp8
Context
524K
Maximum output
524K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

Novita

fp8
Context
1M
Maximum output
131K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

Minimax

fp8
Context
524K
Maximum output
512K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

SambaNova

Not provided
Context
1.0M
Maximum output
944K
Input
$0.6
Output
$2.4
Cache read
Not provided
Cache write
Not provided

ModelRun

fp4
Context
1.0M
Maximum output
944K
Input
$0.75
Output
$3
Cache read
$0.15
Cache write
Not provided
minimax

4 models

All models
minimax logominimax

MiniMax: MiniMax M3.1 Flash

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...

Context
1.0M
Input
text · image · video
Output
text
Input: $0.15Output: $0.6per 1M tokens
View model details →
minimax logominimax

MiniMax: H3 Max

MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...

Context
Not provided
Input
text · image
Output
video
Video output: $0.08 per second
View model details →
minimax logominimax

MiniMax: H3

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...

Context
Not provided
Input
text · image · video · audio
Output
video
Video output: $0.13 per secondReference Image (first 5 free): $0.04 per image
View model details →
minimax logominimax

MiniMax: Speech 2.8 HD

MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Context
Not provided
Input
text
Output
speech
Characters: $100 per million characters
View model details →