MiniMax logo

MiniMax M2.7

Pricing & Specs API
Free REST API for prices, specs and benchmarks
MiniMax M2.7 is MiniMax's language model with a 1.0M context window and up to 131K output tokens, available from 6 providers, starting at $0.25 / 1M input and $0.55 / 1M output. MiniMax's M2.7 MoE language model with vision support and advanced agent capabilities, designed for complex multi-step productivity tasks and dynamic tool use.
Specifications
Canonical IDminimax-m2-7
TypeLanguage
StatusActive
CreatorMiniMaxMiniMax
Providers
Context Window1.0M tokens
Max Output131K tokens
Input ModalitiesImagePDFText
Output ModalitiesText
Reasoning Effortsdefault
Parameters229B
HuggingFace Likes1,015
HuggingFace Downloads (30d)358,255
HuggingFace Downloads (all-time)358,255
Release Date · 4 months ago
Benchmarks
Intelligence Index
38.1
#43
Coding Index
52.6
#35
GPQA
0.9
#43
HLE
0.3
#44
IFBench
0.8
#26
Time to First Token
1.14s
#385
SciCode
0.5
#38
LCR
0.7
#37
TerminalBench Hard
0.4
#41
TAU2
0.8
#90
Output TPS
52.0
#207

Capabilities

Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Cache Write 5m
$ / 1M
Fireworks AI logo
Fireworks AI
fireworks_ai/minimax-m2p7
$0.3$1.20$0.06N/A
Hugging Face logo
Hugging Face
novita:minimax/minimax-m2.7
$0.3$1.20N/AN/A
OpenRouter logo
OpenRouter
minimax/minimax-m2.7
$0.25$1.00$0.05N/A
Pinstripes
pinstripes/ps/minimax-m2.7
$0.255$0.55N/AN/A
SambaNova logo
SambaNova
sambanova/MiniMax-M2.7
$0.6$2.40N/AN/A
Vercel AI Gateway logo
Vercel AI Gateway
minimax/minimax-m2.7
$0.3$1.20$0.06$0.375

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host MiniMax M2.7, ranked by cheapest on-demand price. The model needs about 549 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
p4de.24xlargeAWS8× A100640 GB$27.45/hrus-east-1
Standard_ND96amsr_A100_v4Azure8× NVIDIA A100 (80GB)640 GB$32.77/hrwestus2
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hrus-east-1
7 more instances can run MiniMax M2.7
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MiniMax M2.71.0M$0.250$0.550Current
MiniMax M2.51.0M$0.150$0.900Available
MiniMax M2.11.0M$0.300$1.20Available

Model IDs

accounts/fireworks/models/minimax-m2p7
fireworks_ai/accounts/fireworks/models/minimax-m2p7
fireworks_ai/minimax-m2p7
huggingface-llm-minimax-m2-7
minimax-m2-7
minimax/minimax-m2.7
MiniMaxAI/MiniMax-M2.7
pinstripes/ps/minimax-m2.7
sambanova/MiniMax-M2.7