LLMversus
Anthropic

Claude Haiku 4

Complete specs, pricing, and benchmark data for Claude Haiku 4 by Anthropic. Last verified 2026-04-20.

VisionMultimodalJSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$1.00

Output / 1M tokens

$5.00

Cached Input / 1M

$0.100

Context & Output

Context Window

200K

Max Output

8,192

TTFT

150ms

Speed

130 tok/s

Benchmarks

Arena ELO

1220

Coding ELO

1195

Reasoning ELO

1185

HumanEval

86.5

MMLU

83

MATH

68.2

GPQA

48.5

Try Claude Haiku 4 API

Start building with Claude Haiku 4

Get API Access→

Price History (Input $/M tokens)

Strengths
  • +Very fast response times
  • +200K context window
  • +Affordable for Anthropic quality
  • +Good instruction following
Limitations
  • -Weaker reasoning than Sonnet/Opus
  • -Smaller max output
  • -Less capable on complex coding

Best For

ChatbotsClassificationCost SensitiveHigh Volume

Compare Claude Haiku 4 with...

vs Claude Opus 4vs Gemini 2.5 Provs o3vs DeepSeek R1vs o1vs Qwen 3 235B MoEvs Gemini Experimental 1206vs GPT-4.5vs DeepSeek R1 (Groq)vs Llama 4 Maverickvs DeepSeek R1 (Together)vs Grok 3
Official Pricing Page →
Your ad here