Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
Anthropic
Anthropic

Claude 3.5 Haiku vs Claude Opus 4.6

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:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Supports tool calls

Claude Opus 4.6 wins:

  • Larger context window
  • Higher intelligence benchmark
  • Better at coding
Price Advantage
Claude 3.5 Haiku
Benchmark Advantage
Claude Opus 4.6
Context Window
Claude Opus 4.6
Speed
Claude 3.5 Haiku

Pricing Comparison

Price Comparison

MetricClaude 3.5 HaikuClaude Opus 4.6Winner
Input (per 1M tokens)$0.80$5.00 Claude 3.5 Haiku
Output (per 1M tokens)$4.00$25.00 Claude 3.5 Haiku
Cache Read (per 1M)$80000.00$500000.00 Claude 3.5 Haiku
Cache Write (per 1M)$1000000.00$6250000.00 Claude 3.5 Haiku
Using a 3:1 input/output ratio, Claude 3.5 Haiku is 84% cheaper overall.

Claude 3.5 Haiku Providers

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

Claude Opus 4.6 Providers

Amazon Bedrock $5.00 (Cheapest)
Google $5.00 (Cheapest)
Anthropic $5.00 (Cheapest)

Benchmark Comparison

6
Benchmarks Compared
0
Claude 3.5 Haiku Wins
3
Claude Opus 4.6 Wins

Benchmark Scores

BenchmarkClaude 3.5 HaikuClaude Opus 4.6Winner
Intelligence Index
Overall intelligence score
18.746.4
Coding Index
Code generation & understanding
10.747.6
MMLU Pro
Academic knowledge
63.4--
GPQA
Graduate-level science
40.884.0
LiveCodeBench
Competitive programming
31.4--
AIME
Competition math
3.3--
Claude Opus 4.6 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
Claude Opus 4.6
1,000,000
tokens
Max output: 128,000 tokens
Claude Opus 4.6 has a 80% larger context window.

Speed Performance

MetricClaude 3.5 HaikuClaude Opus 4.6Winner
Tokens/second49.4 tok/s0.0 tok/s
Time to First Token0.68s0.00s
Claude 3.5 Haiku responds Infinity% faster on average.

Capabilities

Feature Comparison

FeatureClaude 3.5 HaikuClaude Opus 4.6
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude 3.5 HaikuClaude Opus 4.6
LicenseProprietaryProprietary
AuthorAnthropicAnthropic
ReleasedNov 2024Feb 2026

Claude 3.5 Haiku Modalities

Input
textimage
Output
text

Claude Opus 4.6 Modalities

Input
textimage
Output
text

Related Comparisons

Compare Claude 3.5 Haiku with:

Compare Claude Opus 4.6 with:

Frequently Asked Questions

Claude 3.5 Haiku has cheaper input pricing at $0.80/M tokens. Claude 3.5 Haiku has cheaper output pricing at $4.00/M tokens.
Claude Opus 4.6 scores higher on coding benchmarks with a score of 47.6, compared to Claude 3.5 Haiku's score of 10.7.
Claude 3.5 Haiku has a 200,000 token context window, while Claude Opus 4.6 has a 1,000,000 token context window.
Claude 3.5 Haiku supports vision. Claude Opus 4.6 supports vision.