Price Per TokenPrice Per Token
Minimax
Minimax
vs
Qwen
Qwen

MiniMax M2.5 vs Qwen Plus 0728 (thinking)

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

112 out of our 301 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

MiniMax M2.5 wins:

  • Cheaper input tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding

Qwen Plus 0728 (thinking) wins:

  • Larger context window
  • Supports tool calls
Price Advantage
MiniMax M2.5
Benchmark Advantage
MiniMax M2.5
Context Window
Qwen Plus 0728 (thinking)
Speed
MiniMax M2.5

Pricing Comparison

Price Comparison

MetricMiniMax M2.5Qwen Plus 0728 (thinking)Winner
Input (per 1M tokens)$0.30$0.40 MiniMax M2.5
Output (per 1M tokens)$1.20$1.20Tie
Cache Read (per 1M)$30000.00N/A MiniMax M2.5
Using a 3:1 input/output ratio, MiniMax M2.5 is 13% cheaper overall.

MiniMax M2.5 Providers

Minimax $0.30 (Cheapest)
Novita $0.30 (Cheapest)

Qwen Plus 0728 (thinking) Providers

Alibaba $0.40 (Cheapest)

Benchmark Comparison

3
Benchmarks Compared
0
MiniMax M2.5 Wins
0
Qwen Plus 0728 (thinking) Wins

Benchmark Scores

BenchmarkMiniMax M2.5Qwen Plus 0728 (thinking)Winner
Intelligence Index
Overall intelligence score
42.0--
Coding Index
Code generation & understanding
37.4--
GPQA
Graduate-level science
84.8--
MiniMax M2.5 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

MiniMax M2.5
204,800
tokens
Max output: 131,072 tokens
Qwen Plus 0728 (thinking)
1,000,000
tokens
Max output: 32,768 tokens
Qwen Plus 0728 (thinking) has a 80% larger context window.

Speed Performance

MetricMiniMax M2.5Qwen Plus 0728 (thinking)Winner
Tokens/second71.0 tok/sN/A
Time to First Token1.67sN/A

Capabilities

Feature Comparison

FeatureMiniMax M2.5Qwen Plus 0728 (thinking)
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyMiniMax M2.5Qwen Plus 0728 (thinking)
LicenseProprietaryOpen Source
AuthorMinimaxQwen
ReleasedFeb 2026Sep 2025

MiniMax M2.5 Modalities

Input
text
Output
text

Qwen Plus 0728 (thinking) Modalities

Input
text
Output
text

Related Comparisons

Compare MiniMax M2.5 with:

Compare Qwen Plus 0728 (thinking) with:

Frequently Asked Questions

MiniMax M2.5 has cheaper input pricing at $0.30/M tokens. MiniMax M2.5 has cheaper output pricing at $1.20/M tokens.
MiniMax M2.5 scores higher on coding benchmarks with a score of 37.4, compared to Qwen Plus 0728 (thinking)'s score of N/A.
MiniMax M2.5 has a 204,800 token context window, while Qwen Plus 0728 (thinking) has a 1,000,000 token context window.
MiniMax M2.5 does not support vision. Qwen Plus 0728 (thinking) does not support vision.