AI TOOLS RADAR
Explore
All models / MINIMAX
minimax logo
minimax

MiniMax: MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. $0.24 per million input tokens, $0.96 per million output tokens. 204,800 token context window, maximum output of 196,608 tokens. Higher uptime with 8 providers. Includes independent benchmarks from Artificial Analysis.

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
$0.24
/M tokens
Output
$0.96
/M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Moderated
Yes
Default parameters
No
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/minimax-m2.7","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

10 providers

Live providers on OpenRouter

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

OpenRouter

Mara

unknown
Context
197K
Maximum output
177K
Input
$0.240
Output
$0.960
Cache read
Not provided
Cache write
Not provided

DeepInfra

fp8
Context
197K
Maximum output
131K
Input
$0.250
Output
$1.00
Cache read
$0.050
Cache write
Not provided

Novita

fp8
Context
205K
Maximum output
131K
Input
$0.270
Output
$1.08
Cache read
$0.054
Cache write
Not provided

AtlasCloud

fp8
Context
197K
Maximum output
177K
Input
$0.300
Output
$1.20
Cache read
$0.060
Cache write
Not provided

Minimax

fp8
Context
205K
Maximum output
131K
Input
$0.300
Output
$1.20
Cache read
$0.060
Cache write
Not provided

GMICloud

fp8
Context
197K
Maximum output
177K
Input
$0.300
Output
$1.20
Cache read
$0.060
Cache write
Not provided

DeepInfra

fp8
Context
197K
Maximum output
131K
Input
$0.380
Output
$1.70
Cache read
$0.070
Cache write
Not provided

Groq

unknown
Context
197K
Maximum output
131K
Input
$0.600
Output
$1.80
Cache read
Not provided
Cache write
Not provided

SambaNova

unknown
Context
197K
Maximum output
177K
Input
$0.600
Output
$2.40
Cache read
$0.060
Cache write
Not provided

Minimax

fp8
Context
205K
Maximum output
131K
Input
$0.600
Output
$2.40
Cache read
$0.060
Cache write
Not provided
minimax

models

All models
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
Input: FreeOutput: Freeper 1M tokens
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
Input: $100.00Output: Freeper 1M tokens
View model details →
minimax logominimax

MiniMax: Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo 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
Input: $60.00Output: Freeper 1M tokens
View model details →
minimax logominimax

MiniMax: MiniMax M3

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,...

Context
1.0M
Input
text · image · video
Output
text
Input: $0.300Output: $1.20per 1M tokens
View model details →