AI model comparison

Claude Haiku 4.5 vs GPT-4o (2024-08-06)

Side by side comparison of Claude Haiku 4.5 and GPT-4o (2024-08-06) on pricing, benchmark scores, context window, and more.

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.

Input / 1M
$1
Output / 1M
$5
Context
200K

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).

Input / 1M
$2.50
Output / 1M
$10
Context
128K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

anthropic logo

Claude Haiku 4.5

2.2x cheaper for a typical chat

Higher intelligence score

openai logo

GPT-4o (2024-08-06)

7.7 vs 7.4 on Artificial Analysis

Larger context window

anthropic logo

Claude Haiku 4.5

200K vs 128K tokens

Newer release

anthropic logo

Claude Haiku 4.5

Released October 15, 2025

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

anthropic logoClaude Haiku 4.57.4
openai logoGPT-4o (2024-08-06)7.7

Coding index

anthropic logoClaude Haiku 4.543.9
openai logoGPT-4o (2024-08-06)Not available

Agentic index

anthropic logoClaude Haiku 4.58
openai logoGPT-4o (2024-08-06)Not available

Pricing

Claude Haiku 4.5 vs GPT-4o (2024-08-06) API pricing

Per-token API rates. Cheaper option highlighted.

Metricanthropic logoClaude Haiku 4.5openai logoGPT-4o (2024-08-06)
Input tokensPer 1M tokens$1$2.50
Output tokensPer 1M tokens$5$10
Cached input (read)Per 1M tokens$0.10$1.25
Cache writePer 1M tokens$1.25Not available
Web searchPer request$0.01Not available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

anthropic logoClaude Haiku 4.5$4.50
openai logoGPT-4o (2024-08-06)$10

Coding task

30K in, 4K out

anthropic logoClaude Haiku 4.5$50$23 cached
openai logoGPT-4o (2024-08-06)$115$77.50 cached

Long document summary

150K in, 2K out

anthropic logoClaude Haiku 4.5$160$25 cached
openai logoGPT-4o (2024-08-06)$395$207.50 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricanthropic logoClaude Haiku 4.5openai logoGPT-4o (2024-08-06)
Context window200K tokens128K tokens
Max output64K tokens16K tokens
Input typesFile, Image, TextFile, Image, Text
Output typesTextText
Reasoning effort levelsNot availableNot available
Default reasoning effortNot availableNot available
Release dateOctober 15, 2025August 6, 2024

Features

Supported features

API features available for each model.

Metricanthropic logoClaude Haiku 4.5openai logoGPT-4o (2024-08-06)
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedNot supported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedNot supportedSupported
Verbosity controlNot supportedNot supported

Our take

Claude Haiku 4.5 is 2.2x cheaper for a typical chat. GPT-4o (2024-08-06) scores higher on the Artificial Analysis Intelligence Index (7.7 vs 7.4). Claude Haiku 4.5 has the larger context window (200K vs 128K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Claude Haiku 4.5 or GPT-4o (2024-08-06) cheaper?

Claude Haiku 4.5 is cheaper for a typical chat (2K input tokens and 500 output tokens). Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens, while GPT-4o (2024-08-06) costs $2.50 per 1M input tokens and $10 per 1M output tokens.

Which has a bigger context window, Claude Haiku 4.5 or GPT-4o (2024-08-06)?

Claude Haiku 4.5 supports up to 200K tokens of context, compared with 128K for GPT-4o (2024-08-06).

Is Claude Haiku 4.5 smarter than GPT-4o (2024-08-06)?

On the Artificial Analysis Intelligence Index, Claude Haiku 4.5 scores 7.4 and GPT-4o (2024-08-06) scores 7.7, putting GPT-4o (2024-08-06) ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Claude Haiku 4.5 and GPT-4o (2024-08-06) at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Claude Haiku 4.5 and GPT-4o (2024-08-06) answer side by side and keep the better response.

anthropic logoopenai logo

Why choose? Ask both.

Send one prompt to Claude Haiku 4.5 and GPT-4o (2024-08-06) at the same time. Compare the answers side by side and keep the best one.