Side-by-side comparison

Pick up to 4 models. Differences are what matter for picking.

Models
Spec
Anthropic
Claude Haiku 4.5
Verified 2026-04-15
DescriptionFast, low-cost model with frontier-level coding for its tier.
Released2025-10-15
Knowledge cutoff2025-02
Context window200K
Max output64K
Input $/1M$1.00
Output $/1M$5.00
Speed tierFast
Reasoning4/5
Coding4/5
Multilingual4/5
Modalities in
Text
Vision
Modalities out
Text
Tool useYes
JSON modeYes
Open weightsNo
Best use cases
Chat
Rag
Summarization
Structured Output
Best personas
Startup
Consumer
Education
Weak at
  • · deepest reasoning chains
Compliance
HIPAA-eligibleSOC 2GDPRISO 27001FedRAMP
Data policy
Sources
Tip: hop over to the Recommender to describe a problem and have AI suggest the best fit from this dataset.