Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. MiniMax

MiniMax Latest

Compatibility alias for MiniMax M3 Thinking, retaining its existing request format and structured-output support. The newer MiniMax M3.1 Flash is available separately as minimax/minimax-m3.1-flash and has different request parameter support.

  • Reasoning
  • Vision
  • Tool Calling
  • Structured Output

Added May 3, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.272
Output
$1.07
Cache read
$0.0544
Compare provider prices

Specifications

Context window
512K
Max output
80K

Benchmarks

Leaderboard results

These leaderboards tested MiniMax M3, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026

Epoch Capabilities Index

147.7

#71 of 115

GPQA Diamond

90.9%

#34 of 119

OTIS Mock AIME 2024–2025

71.1%

#88 of 121

Chess Puzzles

17.0%

#68 of 82

Mystery Game Puzzles

8.0%

#72 of 77

EQ-Bench

EQ-Bench data, MIT · Updated Nov 13, 2026

EQ-Bench 4

1140

#23 of 31

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.272$1.07$0.0544N/AN/A
Auto
Auto (Anonymized)
$0.272$1.07$0.0544N/AN/A
CoreWeave
CoreWeave
FP4
US
$0.242$1.01$0.0525N/AN/A
GMICloud
GMICloud
FP8
US
$0.252$1.01$0.0504N/AN/A
>512k$0.504$2.02$0.101
Runware
Runware
10% off
UNK
$0.315$0.284$1.26$1.13$0.063$0.0567N/AN/A
DeepInfra
DeepInfra
FP8
US
$0.294$1.16$0.0588N/AN/A
MiniMax
MiniMax
SG
$0.315$1.26$0.063N/AN/A
Novita
Novita
US
$0.315$1.26$0.063N/AN/A
>524k$0.63$2.52$0.126
Parasail
Parasail
FP8
US
$0.315$1.26$0.063N/AN/A
RunAnywhere (Wally)
RunAnywhere (Wally)
9% off
BF16
US
$0.347$0.315$1.39$1.26$0.0693$0.063N/AN/A
StreamLake
StreamLake
FP8
CN
$0.315$1.26$0.063N/AN/A
Venice
Venice
FP8
US
$0.315$1.26$0.063N/AN/A
Ollama
Ollama
UNK
$0.63$2.52$0.126N/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.63$2.52$0.126N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
ProviderInputOutputCached input
Auto
Autominimax/minimax-m3:thinking
$0.272/M$1.07/M$0.0544/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare MiniMax Latest with similar models from the same provider or model family.

MiniMax M3.1 Flash

minimax/minimax-m3.1-flash

MiniMax M3.1 Flash is a multimodal model for coding, tool use, and long-context work. It accepts text, images, and video and produces text, with a 1,000,000-token context window and up to 524,288 output tokens within the remaining context. Thinking is always enabled, with low, medium, high, xhigh, and max effort levels; max is the default. Thinking tokens count toward the output limit. Temperature is fixed at 1 and top-p at 0.95; custom values have no effect.

MiniMax M3

minimax/minimax-m3

MiniMax M3 is MiniMax's open-weights frontier model, built for coding, agent workflows, tool use, and multimodal understanding from step zero. Thinking stays off for faster direct answers unless a request asks for it; MiniMax M3 Thinking has it on by default. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.

MiniMax M3 Thinking

minimax/minimax-m3:thinking

MiniMax M3 Thinking is the adaptive-thinking version of MiniMax's open-weights frontier model for coding, agent workflows, tool use, long-context tasks, and native multimodal understanding. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.

MiniMax M2.7

minimax/minimax-m2.7

MiniMax M2.7 is the first model deeply involved in iterating on its own training. It excels in real-world software engineering (SWE-Pro 56.22%), end-to-end project delivery (VIBE-Pro 55.6%), and complex office workflows with strong tool-use compliance and agentic capabilities.

MiniMax M2.7 Turbo

minimax/minimax-m2.7-turbo

MiniMax M2.7 Turbo is the highspeed and higher priced route for M2.7.

MiniMax M2.5

minimax/minimax-m2.5

MiniMax M2.5 is a productivity-focused flagship model that builds on M2.1 with stronger coding and real-world office workflow performance (Word, Excel, PowerPoint), plus better tool-use planning and token efficiency.