All models
Official page
Claude Haiku 4.5
liteAnthropic
Anthropic's fastest and most compact model. Ideal for lightweight agents, high-throughput pipelines, and latency-sensitive applications.
fastestlightweightcost-effective
Context
200K
Input / 1M
$1.00
Output / 1M
$5.00
Knowledge cutoff
2025-04
Capabilities
Code4/5
Reasoning3/5
Multilingual4/5
Safety5/5
Speed5/5
Modalities & Features
Vision (image input) Yes
Audio No
Video No
Function / tool calling Yes
JSON mode Yes
Extended thinking No
Context & Output
Context window200K
Max output tokens16K
Knowledge cutoff2025-04
Release date2025-07
API & Access
Open source No
Streaming Yes
Batch API Yes
Prompt caching Yes
Fine-tuning No
Benchmarks
MMLUGeneral knowledge
80.1%GPQA DiamondHard science Q&A
N/AMATHMath problem solving
N/AAIME 2025Advanced math
N/AGSM8KGrade-school math
N/AHumanEvalCode generation
N/ALiveCodeBenchLive coding problems
N/ASWE-bench VerifiedReal-world software
N/AHellaSwagCommonsense inference
N/ASource: provider technical reports & independent evaluations. N/A = not yet published for this model.
Pricing (per 1M tokens)
Input$1.00
Output$5.00
Prices shown are list prices and may vary by provider plan. Always check official documentation for the latest pricing.