Skip to content
LLMs
MiniMax logo

MiniMax: MiniMax M3

by MiniMax

MiniMax: MiniMax M3 is a large language model from MiniMax. It costs $0.300 per million input tokens and $1.20 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weightsimage inputvideo input
Input / 1M tokens
$0.300
Output / 1M tokens
$1.20
Cached input / 1M
$0.060

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

12 hosts serve MiniMax M3. Same weights, same API - the price difference is pure margin and routing.

Providers serving MiniMax: MiniMax M3, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
CoreWeaveCheapestfp4$0.230$0.960262K-100.0%
GMICloudfp8$0.240$0.9601.0M-99.5%
DeepInfrafp8$0.280$1.10524K-96.4%
StreamLakefp8$0.300$1.201M-98.6%
Venicefp8$0.300$1.20524K-95.5%
Together$0.300$1.20524K-99.0%
Parasailfp8$0.300$1.201.0M-99.2%
AtlasCloudfp8$0.300$1.20524K-98.8%
Novitafp8$0.300$1.201M-99.6%
Minimaxfp8$0.300$1.20524K-98.5%
SambaNova$0.600$2.401.0M-99.4%
ModelRunfp4$0.750$3.001.0M-99.9%

The spread between CoreWeave and ModelRun is 3.2× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
29.6
Coding index
58.6
Agentic index
30.8

About 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,...

Specifications

MiniMax: MiniMax M3 specifications
Model IDminimax/minimax-m3
ProviderMiniMax
Context window1.0M tokens
Max output512K tokens
Input modalitiestext, image, video
Output modalitiestext
Knowledge cutoff-
Open weightsYes - MiniMaxAI/Minimax-M3
ReleasedMay 31, 2026

Cheaper alternatives

Models that cost less than MiniMax M3 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does MiniMax: MiniMax M3 cost?

$0.300 per million input tokens and $1.20 per million output tokens. Cached input reads cost $0.060 per million tokens.

What is the context window of MiniMax: MiniMax M3?

1.0M tokens, with up to 512K tokens of output per request.

Which provider serves MiniMax: MiniMax M3 cheapest?

CoreWeave at $0.230 per million input tokens - 3.2× cheaper than ModelRun, the most expensive of the 12 hosts serving it.

Confirm against the source: MiniMax official pricing.