Anthropic

Claude 3.5 Haiku

anthropic/claude-3.5-haiku

200K context·8.2K max output·text+image->text

Input

$0.8000

per 1M tokens

Output

$4.00

per 1M tokens

Cache Read

-

not available

Cache Write

-

not available

Quality Benchmarks

FrontierValue: 73.7

Coding

Code generation, completion, debugging

66.6

Math

Competition math, calculus, olympiad

66.6

Reasoning

Logic, spatial, puzzle solving

66.6

Language

Summarization, paraphrase, writing

66.6

Overall

66.6

Source: LiveBench (livebench.ai) / Scores 0-100

Capabilities

VisionTool UseReasoningPrompt Caching

Similar Price Range

More from Anthropic

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.