Claude 3.5 Sonnet vs GPT-4o-mini

API pricing, context window and capabilities for Claude 3.5 Sonnet and GPT-4o-mini, 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 Sonnet wins on context window. GPT-4o-mini wins on price. Benchmark data is unavailable for one or both models.

Price
GPT-4o-mini
Coding
Not called
Intelligence
Not called
Context window
Claude 3.5 Sonnet

Key takeaways

who wins on what, from the published numbers

Claude 3.5 Sonnet wins

  • Larger context window (200K vs 131K)

GPT-4o-mini wins

  • Cheaper input ($3.00 vs $0.15 /1M)
  • Cheaper output ($15.00 vs $0.60 /1M)
Cheaper overall
GPT-4o-mini
$0.15 + $0.60 /1M
Larger context
Claude 3.5 Sonnet
200K
More providers
Tied

Pricing & specs

cheapest serving route · per 1M tokens
Claude 3.5 SonnetGPT-4o-mini
Input $/1M$3.00 $0.15 best
Output $/1M$15.00 $0.60 best
Context window200K best131K
Max output16K 16K
Serving providers5 5
Releasedn/a 2024-07-18

Benchmarks

Artificial Analysis indices, side by side
Claude 3.5 SonnetGPT-4o-mini
IntelligenceNot available 6.9
CodingNot available 11.4
GPQA DiamondNot available 43%
Output speedNot available 47 t/s
Latency (TTFT)Not available 6.68s

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude 3.5 Sonnet
via OpenRouter
$30
GPT-4o-mini
via Azure
$1.35

Capabilities

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

Related comparisons

Frequently asked questions

Which is cheaper, Claude 3.5 Sonnet or GPT-4o-mini?
GPT-4o-mini is cheaper for input ($3.00 vs $0.15 per 1M tokens). GPT-4o-mini is cheaper for output ($15.00 vs $0.60 per 1M tokens).
What is the context window difference between Claude 3.5 Sonnet and GPT-4o-mini?
Claude 3.5 Sonnet has a 200K-token context window and GPT-4o-mini has 131K tokens, so Claude 3.5 Sonnet can take a larger prompt.
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