LLMversus
Anthropic

Claude 3.5 Haiku

Complete specs, pricing, and benchmark data for Claude 3.5 Haiku by Anthropic. Last verified 2026-04-20.

JSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$0.800

Output / 1M tokens

$4.00

Context & Output

Context Window

200K

Max Output

8,192

TTFT

150ms

Speed

100 tok/s

Benchmarks

Arena ELO

1220

Coding ELO

1250

Reasoning ELO

1220

HumanEval

85

MMLU

83

MATH

96

GPQA

40

Try Claude 3.5 Haiku API

Start building with Claude 3.5 Haiku

Get API Access→

Price History (Input $/M tokens)

Strengths
  • +Very cheap
  • +Fast
  • +Large context
Limitations
  • -Weaker reasoning
  • -Smaller model

Best For

Cost EffectiveCodingFast Inference

Compare Claude 3.5 Haiku 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