← Back to Calculator

DeepSeek V4 Pro vs MiniMax M3

Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.

Cost at a Glance

DeepSeek V4 Pro and MiniMax M3 have identical pricing at standard rates.

At 5M input + 2M output tokens per month:

DeepSeek V4 Pro$3.92/movsMiniMax M3$3.90/mo

Choosing MiniMax M3 could save you $0.02/mo

Price Comparison (per 1M tokens)

Input (per 1M tokens)
$0.43vs$0.30
Output (per 1M tokens)
$0.87vs$1.20
Cache Write (per 1M tokens)
$0.43vs
Cache Read (per 1M tokens)
$0.00vs
Batch Input (per 1M tokens)
vs
Batch Output (per 1M tokens)
vs

Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →

Specifications

Context Window
1Mvs1M
Max Output Tokens
128Kvs64K
Knowledge Cutoff
2026-05vs2026-04
Modalities
TextvsText
Prompt Caching
NovsNo
Batch API
NovsNo
Thinking / Reasoning
YesvsNo

Benchmark Scores

SWE-bench Verified
80.6vs80.5
MMLU-Pro
84.0vs82.5
HumanEval
93.8vs92.0

Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.

Use Cases

DeepSeek V4 Pro

cheapcodingopen-weight

MiniMax M3

codingcheapopen-weight

About the Providers

DeepSeek V4 Pro is developed by DeepSeek. MiniMax M3 is developed by MiniMax. This is a cross-provider comparison between DeepSeek and MiniMax models. For the most up-to-date pricing, always check the official API documentation from each provider.

Compare More AI Models