DeepSeek V4 Pro vs MiniMax M3

API pricing, context window and capabilities for DeepSeek V4 Pro and MiniMax M3, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

DeepSeek V4 Pro wins on coding. MiniMax M3 wins on intelligence.

Price
Tied
Coding
DeepSeek V4 Pro
Intelligence
MiniMax M3
Context window
Tied

Key takeaways

who wins on what, from the published numbers

DeepSeek V4 Pro wins

  • Cheaper output ($0.87 vs $1.20 /1M)
  • More serving providers (4 vs 2)

MiniMax M3 wins

  • Cheaper input ($0.43 vs $0.30 /1M)
  • Higher max output (384K vs 512K)
  • Supports vision
Cheaper overall
DeepSeek V4 Pro
$0.43 + $0.87 /1M
Larger context
Tied
More providers
DeepSeek V4 Pro
4 providers

Pricing & specs

cheapest serving route · per 1M tokens
DeepSeek V4 ProMiniMax M3
Input $/1M$0.43 $0.30 best
Output $/1M$0.87 best$1.20
Context window1M 1M
Max output384K 512K best
Serving providers4 best2
Released2026-04-24 2026-06-01

Benchmarks

Artificial Analysis indices, side by side
DeepSeek V4 ProMiniMax M3
Intelligence44.3 44.4 best
Coding59.4 best58.6
GPQA Diamond89% 93% best
Output speed75 t/s 85 t/s best
Latency (TTFT)7.80s 5.28s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
DeepSeek V4 Pro
via Tencent
$3.04
MiniMax M3
via Fireworks AI
$2.70

Capabilities

feature support, side by side
FeatureDeepSeek V4 ProMiniMax M3
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, DeepSeek V4 Pro or MiniMax M3?
MiniMax M3 is cheaper for input ($0.43 vs $0.30 per 1M tokens). DeepSeek V4 Pro is cheaper for output ($0.87 vs $1.20 per 1M tokens).
What is the context window difference between DeepSeek V4 Pro and MiniMax M3?
Both DeepSeek V4 Pro and MiniMax M3 have about a 1M-token context window.
How do DeepSeek V4 Pro and MiniMax M3 compare on benchmarks?
On the tracked Artificial Analysis indices, DeepSeek V4 Pro leads on coding, and MiniMax M3 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI