Back to Explore
MiniMax: MiniMax M3
MiniMax·Released 2026-05-31
1.0M ctxMultimodal
Comparison data ready93% coverage16/16 fields directly observedUpdated Jul 15, 2026, 10:30 PM
About
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,...
Related Models
Pricing
Input
$0.30
per 1M tokens
Output
$1.20
per 1M tokens
Blended
$0.52
per 1M tokens
Cheaper than 54% of models. Median price is $0.68/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.52
Monthly
$15.75
vs. Similar Models
DeepSeek: DeepSeek V4 ProQ:-0.1
$0.54+4%
OpenAI: GPT-5.3-CodexQ:-0.1
$4.81+817%
MoonshotAI: Kimi K2.6Q:-0.2
$1.35+157%
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Q:-0.7
$10.00+1805%
Performance
105
tokens/sec
Faster than 58% of models
1.49
seconds
Faster than 33% of models
20.54
seconds
Faster than 27% of models
Market Median
93 tok/s
12% faster
Median TTFT
1.09s
36% slower
Throughput/Dollar
200
tok/s per $/1M
Speed Comparison
Llama 2 Chat 7B
105 tok/s+0%
Qwen3 Omni 30B A3B (Reasoning)
105 tok/s-0%
GPT-5.4 (Non-reasoning)
104 tok/s-1%
Context Window
1.0M
tokens
Larger than 89% of models
Max Output
512K
tokens
49% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
92.9%
HLE
37.1%
LiveCodeBenchNot evaluated
SciCode
45.4%
TerminalBench Hard
42.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
82.9%
Long Context Recall
74.0%
Tau2
88.9%
Market AverageTop Score