← Back to all models
C

Claude Haiku 4.5

by Anthropic
Efficient Paid API Multimodal 🏆 Ranked #53 of 85
69.5
Overall Score
out of 100
About

Anthropic's fastest and most affordable vision model with a 200K context window. Ideal for high-volume tasks requiring speed and vision capability at minimal cost.

Key Metrics
Context Window
200K
tokens
Avg Response
380
milliseconds
Input Cost
$0.8
per million tokens
Output Cost
$4.0
per million tokens
Arena ELO
1230
Chatbot Arena rating
MT-Bench
8.5
out of 10
Benchmark Scores
MMLU
78.0%
HumanEval
78.0%
MATH
68.0%
GPQA
45.0%
MT-Bench
85.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Very fast ✓ Low cost ✓ Vision capable ✓ Long context ✓ High throughput
Limitations
⚠ Less capable than Sonnet/Opus ⚠ Limited complex reasoning ⚠ Smaller knowledge depth
Ideal Use Cases
Chatbots High-volume automation Quick vision tasks Summarisation Classification
Model Details
Provider Anthropic
Released 2025-05-15
Type Paid API
Multimodal Yes
Tier Efficient
Global rank #53 / 85
Pricing (USD)
Input tokens $0.8/M
Output tokens $4.0/M
Per 1,000 tokens ≈ $0.0008 input / $0.0040 output
All Benchmarks
MMLU 78.0%
HumanEval 78.0%
MATH 68.0%
GPQA 45.0%
MT-Bench 8.5/10
Arena ELO 1230
Compare this model View Rankings

You might also consider