PriceIndex
Anthropic logo

Claude Haiku 4.5

claude-haiku-4.5
APIProvider site

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... Built by Anthropic.

Prices updated

Input price

$1.00

per 1M tokens · Standard

Output price

$5.00

per 1M tokens · Standard

Input limit

200K

tokens

Output limit

64K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF
Compare

Claude Haiku 4.5 price history

2 price records since 9/25/2026

Claude Haiku 4.5 cost calculator

Input20M tokens
Output5M tokens

$45/month

Standard pricing

    Overview

    What is Claude Haiku 4.5?

    Claude Haiku 4.5 is a text & reasoning and vision model from Anthropic. Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... Its 200K context window and $1.00 input price make it a candidate for quality-focused production applications.

    Image understandingDocument analysisContent workflowsClassification

    Benchmarks

    Claude Haiku 4.5 benchmarks & speed

    How Claude Haiku 4.5 scores on standardized evaluations, and where it lands among every model we track.

    15.4

    Intelligence Index

    Better than 39% of 153 models

    84tok/s

    Output speed

    Better than 42% of 119 models

    1118

    DesignArena Elo

    Better than 21% of 81 models

    Reasoning

    GPQA Diamond

    64.6%

    Graduate-level scientific reasoning · top 77%

    HLE

    4.2%

    Humanity's Last Exam · top 88%

    Latency & design

    Time to first token
    0.55s
    DesignArena win rate
    44.9%
    Design battles judged
    35,541

    Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.

    Rates

    Claude Haiku 4.5 pricing

    Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

    Input · Standard

    $1.00

    Per 1M tokens

    Cached input · Standard

    $0.10

    Per 1M tokens

    Capabilities

    Claude Haiku 4.5 Tools

    Tools available when using Claude Haiku 4.5 through supported provider APIs.

    Function calling

    Supported

    Structured outputs

    Supported

    JSON mode

    Supported

    Reasoning

    Supported

    Built-in web search

    Not supported

    Log probabilities

    Not supported

    Deterministic seed

    Not supported

    Parallel tool calls

    Not supported

    Prompt caching

    Supported

    Strengths and limitations

    Strengths

    • Measured results (AA Intelligence 15.4 · DesignArena Elo 1118) position it for demanding production work.
    • 200K context supports large documents, repositories and extended conversations.
    • Supports text & reasoning and vision workloads in one model.

    Limitations

    • Generated tokens cost 5× more than input tokens, which matters for verbose responses.
    • Large context capacity does not guarantee consistent retrieval across the entire prompt.
    • Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

    Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

    Same provider

    More models from Anthropic

    View provider →
    200K

    $0.25 in · $1.25 out

    View model
    1M

    $10 in · $50 out

    View model
    1M

    $10 in · $50 out

    View model
    1M

    $0.10 in · $0.50 out

    View model

    Frequently asked questions about Claude Haiku 4.5

    Claude Haiku 4.5 is a text & reasoning and vision model from Anthropic. Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...