Claude 3 Haiku vs GPT-4o

API pricing, context window and capabilities for Claude 3 Haiku and GPT-4o, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Claude 3 Haiku wins on price and on context window. GPT-4o wins on intelligence. Benchmark data is unavailable for one or both models.

Price
Claude 3 Haiku
Coding
Not called
Intelligence
GPT-4o
Context window
Claude 3 Haiku

Key takeaways

who wins on what, from the published numbers

Claude 3 Haiku wins

  • Cheaper input ($0.25 vs $2.50 /1M)
  • Cheaper output ($1.25 vs $10.00 /1M)
  • Larger context window (200K vs 131K)

GPT-4o wins

  • Higher max output (4K vs 16K)
  • More serving providers (3 vs 6)
  • Supports audio
  • Supports prompt caching
Cheaper overall
Claude 3 Haiku
$0.25 + $1.25 /1M
Larger context
Claude 3 Haiku
200K
More providers
GPT-4o
6 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude 3 HaikuGPT-4o
Input $/1M$0.25 best$2.50
Output $/1M$1.25 best$10.00
Context window200K best131K
Max output4K 16K best
Serving providers3 6 best
Releasedn/a 2024-05-13

Benchmarks

Artificial Analysis indices, side by side
Claude 3 HaikuGPT-4o
Intelligence3.9 11.2 best
GPQA Diamond37% 54% best
Output speedNot available 99 t/s
Latency (TTFT)Not available 5.19s

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude 3 Haiku
via OpenRouter
$2.50
GPT-4o
via Azure
$23

Capabilities

feature support, side by side
FeatureClaude 3 HaikuGPT-4o
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude 3 Haiku or GPT-4o?
Claude 3 Haiku is cheaper for input ($0.25 vs $2.50 per 1M tokens). Claude 3 Haiku is cheaper for output ($1.25 vs $10.00 per 1M tokens).
What is the context window difference between Claude 3 Haiku and GPT-4o?
Claude 3 Haiku has a 200K-token context window and GPT-4o has 131K tokens, so Claude 3 Haiku can take a larger prompt.
How do Claude 3 Haiku and GPT-4o compare on benchmarks?
On the tracked Artificial Analysis indices, GPT-4o leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI