Claude 4.5 Haiku
ClaudeCompact
ThinkingTool UseVisionStructured Output
About this model
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Performance Tier
Compact
Claude 4.5 Haiku is a compact model from Claude : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $1.00 |
| Output (completion) | $5.00 |
| Cache read | $0.100 |
| Cache write | $1.25 |
Capabilities
Context Length200K
Max Output Tokens64K
TokenizerClaude
Inputimage, text
Outputtext
Release DateOctober 15, 2025
Benchmarks
General Intelligence
MMLU
82.6%
Mathematics
MATH-500
69%
AIME 2025
80.7%
Programming
HumanEval
88.1%
Recommended Use Cases
CodingGeneral ChatSummarizationCustomer Support
Strengths
- Fastest Claude model — ideal for high-throughput applications
- Lowest cost in the Claude family
- Strong coding performance for its size (HumanEval 88.1%)
- Excellent for classification, summarization and extraction
Limitations
- Limited complex reasoning compared to Sonnet/Opus
- Shorter context window than larger Claude models
Resources
This model may use your data for training
