AI TOOLS RADAR
All models / MINIMAX
minimax logo
minimax

MiniMax: MiniMax M2.5

Source description (English)

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
204,800 tokens
Maximum output
131,072 tokens
Architecture
text->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
$0.03
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Reasoning required
Yes
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-m2.5","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

8 providers

Checked: October 25, 2026

Live providers on OpenRouter

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

OpenRouter

Venice

Not provided
Context
198K
Maximum output
33K
Input
$0.27
Output
$0.95
Cache read
$0.03
Cache write
Not provided

StreamLake

Not provided
Context
200K
Maximum output
128K
Input
$0.27
Output
$1.08
Cache read
$0.027
Cache write
Not provided

AtlasCloud

fp8
Context
197K
Maximum output
177K
Input
$0.295
Output
$1.2
Cache read
$0.06
Cache write
Not provided

GMICloud

fp8
Context
197K
Maximum output
177K
Input
$0.3
Output
$1.2
Cache read
$0.03
Cache write
Not provided

DigitalOcean

Not provided
Context
66K
Maximum output
59K
Input
$0.3
Output
$1.2
Cache read
$0.06
Cache write
Not provided

Novita

fp8
Context
205K
Maximum output
131K
Input
$0.3
Output
$1.2
Cache read
$0.03
Cache write
Not provided

Minimax

fp8
Context
205K
Maximum output
131K
Input
$0.3
Output
$1.2
Cache read
$0.03
Cache write
Not provided

Minimax

fp8
Context
205K
Maximum output
131K
Input
$0.6
Output
$2.4
Cache read
$0.06
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 →