Back to the index
Anthropic · Claude
No. 06

Claude Haiku 4.5

Fastest, cheapest Claude — snappy everyday tasks at scale.

FastClosed weightsText, Image, Pdf
Field notes
Context window
200Ktokens
Max output
64Ktokens
Input price
$1/ 1M tokens
Output price
$5/ 1M tokens
Cached input
$0.10/ 1M tokens
Modalities
Text, Image, Pdf
Knowledge cutoff
Jul 2025
Released
Oct 2025
Approx. speed
—
Overview

What this model is

Claude Haiku 4.5 is Anthropic's fastest and cheapest model, built for high-volume, latency-sensitive work. It delivers surprisingly strong reasoning and coding for its price and is a great router target for the bulk of simpler traffic. Escalate to Sonnet or Opus when a task needs deeper reasoning or long-horizon reliability.

Strengths

  • Fastest and cheapest Claude
  • Strong quality for its tier
  • Great for high-volume routing
  • Low latency for real-time work
  • 200K context

Trade-offs

  • Smaller 200K context vs 1M on higher tiers
  • Not for hard long-horizon agentic work
  • Lower peak reasoning than larger Claude models

Best for

  • High-volume classification and extraction
  • Low-latency chat and autocomplete
  • Simple coding and edits
  • Cheap agent sub-steps

Not ideal for

  • Complex autonomous coding
  • Deep multi-step reasoning tasks
  • Very long-context tasks (>200K)
Capabilities

Capability profile

Normalized 0–100 scores, comparable across the whole catalog.

Reasoning78Coding78Math80Writing82Knowledge80Speed93Agentic75Vision78Multilingual82Long Context80
Reasoning
78
Coding
78
Math
80
Writing
82
Knowledge
80
Speed
93
Agentic
75
Vision
78
Multilingual
82
Long Context
80
Benchmarks

How it scores

Public benchmark results, with independent third-party results where available. Bars normalize percentages to 100 and Elo ratings to a 1500 ceiling.

Independent index
Artificial Analysis Intelligence Index
Composite of ~9–10 independent evals · Artificial Analysis
30/ 100
BenchmarkResult
Artificial Analysis Intelligence Indexindependent
GeneralArtificial Analysis
30%
SWE-bench Verifiedindependent
CodingSWE-bench
73.3%
SWE-bench Proindependent
CodingSWE-bench Pro
39.5%
AIME 2025
MathVendor-reported
80.7%
Alternatives

Comparable models

Models in a roughly similar class — worth weighing against this one.

GPT-5.4 miniOpenAI

Affordable OpenAI workhorse for standard production routing.

GPT-5.4 nanoOpenAI

OpenAI's cheapest small model for high-volume simple work.

Gemini 3.5 FlashGoogle DeepMind

Fast, cheap multimodal workhorse with near-Pro quality.