Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
Minimax
Minimax

Claude 3.5 Haiku vs MiniMax M2.5

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

Claude 3.5 Haiku wins:

  • Supports vision
  • Supports tool calls

MiniMax M2.5 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
Price Advantage
MiniMax M2.5
Benchmark Advantage
MiniMax M2.5
Context Window
MiniMax M2.5
Speed
MiniMax M2.5

Pricing Comparison

Price Comparison

MetricClaude 3.5 HaikuMiniMax M2.5Winner
Input (per 1M tokens)$0.80$0.30 MiniMax M2.5
Output (per 1M tokens)$4.00$1.20 MiniMax M2.5
Cache Read (per 1M)$80000.00$30000.00 MiniMax M2.5
Cache Write (per 1M)$1000000.00N/A Claude 3.5 Haiku
Using a 3:1 input/output ratio, MiniMax M2.5 is 67% cheaper overall.

Claude 3.5 Haiku Providers

Vercel $0.80 (Cheapest)
Amazon Bedrock $0.80 (Cheapest)
Google $0.80 (Cheapest)
Anthropic $0.80 (Cheapest)

MiniMax M2.5 Providers

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

Benchmark Comparison

6
Benchmarks Compared
0
Claude 3.5 Haiku Wins
3
MiniMax M2.5 Wins

Benchmark Scores

BenchmarkClaude 3.5 HaikuMiniMax M2.5Winner
Intelligence Index
Overall intelligence score
18.742.0
Coding Index
Code generation & understanding
10.737.4
MMLU Pro
Academic knowledge
63.4--
GPQA
Graduate-level science
40.884.8
LiveCodeBench
Competitive programming
31.4--
AIME
Competition math
3.3--
MiniMax M2.5 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Claude 3.5 Haiku
Other models

Context & Performance

Context Window

Claude 3.5 Haiku
200,000
tokens
Max output: 8,192 tokens
MiniMax M2.5
204,800
tokens
Max output: 131,072 tokens
MiniMax M2.5 has a 2% larger context window.

Speed Performance

MetricClaude 3.5 HaikuMiniMax M2.5Winner
Tokens/second49.4 tok/s71.0 tok/s
Time to First Token0.68s1.67s
MiniMax M2.5 responds 44% faster on average.

Capabilities

Feature Comparison

FeatureClaude 3.5 HaikuMiniMax M2.5
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude 3.5 HaikuMiniMax M2.5
LicenseProprietaryProprietary
AuthorAnthropicMinimax
ReleasedNov 2024Feb 2026

Claude 3.5 Haiku Modalities

Input
textimage
Output
text

MiniMax M2.5 Modalities

Input
text
Output
text

Related Comparisons

Compare Claude 3.5 Haiku with:

Compare MiniMax M2.5 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 Claude 3.5 Haiku's score of 10.7.
Claude 3.5 Haiku has a 200,000 token context window, while MiniMax M2.5 has a 204,800 token context window.
Claude 3.5 Haiku supports vision. MiniMax M2.5 does not support vision.