DeepSeek V4 Pro 0423 vs MiniMax M3

API pricing, context window and capabilities for DeepSeek V4 Pro 0423 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 0423 wins on coding and on intelligence.

Price
Tied
Coding
DeepSeek V4 Pro 0423
Intelligence
DeepSeek V4 Pro 0423
Context window
Tied

Key takeaways

who wins on what, from the published numbers

DeepSeek V4 Pro 0423 wins

  • Cheaper output ($0.87 vs $0.96 /1M)
  • More serving providers (10 vs 8)

MiniMax M3 wins

  • Cheaper input ($0.43 vs $0.23 /1M)
  • Higher max output (512K vs 524K)
  • Supports vision
Cheaper overall
MiniMax M3
$0.23 + $0.96 /1M
Larger context
Tied
More providers
DeepSeek V4 Pro 0423
10 providers

Pricing & specs

cheapest serving route · per 1M tokens
DeepSeek V4 Pro 0423MiniMax M3
Input $/1M$0.43 $0.23 best
Output $/1M$0.87 best$0.96
Context window1M 1M
Max output512K 524K best
Serving providers10 best8
Released2026-04-24 2026-06-01

Benchmarks

Artificial Analysis indices, side by side
DeepSeek V4 Pro 0423MiniMax M3
Intelligence53.2 best45.4
Coding68.8 best58.6
GPQA Diamond93% 93%
Output speed68 t/s 108 t/s best
Latency (TTFT)1.75s 1.08s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
DeepSeek V4 Pro 0423
via Tencent
$3.04
MiniMax M3
via Wandb
$2.11

Capabilities

feature support, side by side
FeatureDeepSeek V4 Pro 0423MiniMax M3
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, DeepSeek V4 Pro 0423 or MiniMax M3?
MiniMax M3 is cheaper for input ($0.43 vs $0.23 per 1M tokens). DeepSeek V4 Pro 0423 is cheaper for output ($0.87 vs $0.96 per 1M tokens).
What is the context window difference between DeepSeek V4 Pro 0423 and MiniMax M3?
Both DeepSeek V4 Pro 0423 and MiniMax M3 have about a 1M-token context window.
How do DeepSeek V4 Pro 0423 and MiniMax M3 compare on benchmarks?
On the tracked Artificial Analysis indices, DeepSeek V4 Pro 0423 leads on coding, and DeepSeek V4 Pro 0423 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