Claude 3.5 Haiku vs GPT-4o

API pricing, context window and capabilities for Claude 3.5 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 3.5 Haiku wins on price, on intelligence and on context window. Benchmark data is unavailable for one or both models.

Price
Claude 3.5 Haiku
Coding
Not called
Intelligence
Claude 3.5 Haiku
Context window
Claude 3.5 Haiku

Key takeaways

who wins on what, from the published numbers

Claude 3.5 Haiku wins

  • Cheaper input ($0.80 vs $2.50 /1M)
  • Cheaper output ($4.00 vs $10.00 /1M)
  • Larger context window (200K vs 131K)

GPT-4o wins

  • Higher max output (8K vs 16K)
  • More serving providers (3 vs 6)
  • Supports audio
Cheaper overall
Claude 3.5 Haiku
$0.80 + $4.00 /1M
Larger context
Claude 3.5 Haiku
200K
More providers
GPT-4o
6 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude 3.5 HaikuGPT-4o
Input $/1M$0.80 best$2.50
Output $/1M$4.00 best$10.00
Context window200K best131K
Max output8K 16K best
Serving providers3 6 best
Released2024-10-22 2024-05-13

Benchmarks

Artificial Analysis indices, side by side
Claude 3.5 HaikuGPT-4o
Intelligence12.3 best11.2
Coding15.9 Not available
GPQA Diamond41% 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 3.5 Haiku
via Vercel AI Gateway
$8.00
GPT-4o
via Azure
$23

Capabilities

feature support, side by side
FeatureClaude 3.5 HaikuGPT-4o
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude 3.5 Haiku or GPT-4o?
Claude 3.5 Haiku is cheaper for input ($0.80 vs $2.50 per 1M tokens). Claude 3.5 Haiku is cheaper for output ($4.00 vs $10.00 per 1M tokens).
What is the context window difference between Claude 3.5 Haiku and GPT-4o?
Claude 3.5 Haiku has a 200K-token context window and GPT-4o has 131K tokens, so Claude 3.5 Haiku can take a larger prompt.
How do Claude 3.5 Haiku and GPT-4o compare on benchmarks?
On the tracked Artificial Analysis indices, Claude 3.5 Haiku 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