GPT-4 Turbo vs GPT-4o-mini

API pricing, context window and capabilities for GPT-4 Turbo 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

GPT-4 Turbo wins on coding and on intelligence. GPT-4o-mini wins on price and on context window.

Price
GPT-4o-mini
Coding
GPT-4 Turbo
Intelligence
GPT-4 Turbo
Context window
GPT-4o-mini

Key takeaways

who wins on what, from the published numbers

GPT-4 Turbo wins

No clear edge on the tracked metrics.

GPT-4o-mini wins

  • Cheaper input ($10.00 vs $0.15 /1M)
  • Cheaper output ($30.00 vs $0.60 /1M)
  • Larger context window (128K vs 131K)
  • Higher max output (4K vs 16K)
  • More serving providers (3 vs 5)
  • Supports structured output
Cheaper overall
GPT-4o-mini
$0.15 + $0.60 /1M
Larger context
GPT-4o-mini
131K
More providers
GPT-4o-mini
5 providers

Pricing & specs

cheapest serving route · per 1M tokens
GPT-4 TurboGPT-4o-mini
Input $/1M$10.00 $0.15 best
Output $/1M$30.00 $0.60 best
Context window128K 131K best
Max output4K 16K best
Serving providers3 5 best
Released2023-11-06 2024-07-18

Benchmarks

Artificial Analysis indices, side by side
GPT-4 TurboGPT-4o-mini
Intelligence7.9 best6.9
Coding21.5 best11.4
GPQA DiamondNot available 43%
Output speed12 t/s 47 t/s best
Latency (TTFT)19.20s 6.68s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
GPT-4 Turbo
via Azure
$80
GPT-4o-mini
via Azure
$1.35

Capabilities

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

Related comparisons

Frequently asked questions

Which is cheaper, GPT-4 Turbo or GPT-4o-mini?
GPT-4o-mini is cheaper for input ($10.00 vs $0.15 per 1M tokens). GPT-4o-mini is cheaper for output ($30.00 vs $0.60 per 1M tokens).
What is the context window difference between GPT-4 Turbo and GPT-4o-mini?
GPT-4 Turbo has a 128K-token context window and GPT-4o-mini has 131K tokens, so GPT-4o-mini can take a larger prompt.
How do GPT-4 Turbo and GPT-4o-mini compare on benchmarks?
On the tracked Artificial Analysis indices, GPT-4 Turbo leads on coding, and GPT-4 Turbo 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