GPT-4 vs GPT-4o-mini
API pricing, context window and capabilities for GPT-4 and GPT-4o-mini, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersGPT-4o-mini wins on price and on context window. Benchmark data is unavailable for one or both models.
Price
GPT-4o-mini
Terminal-Bench
Not called
Intelligence
Tied
Context window
GPT-4o-mini
Key takeaways
who wins on what, from the published numbersGPT-4 wins
No clear edge on the tracked metrics.
GPT-4o-mini wins
- Cheaper input ($30.00 vs $0.15 /1M)
- Cheaper output ($60.00 vs $0.60 /1M)
- Larger context window (8K vs 131K)
- Higher max output (4K vs 16K)
- More serving providers (3 vs 6)
- Supports vision
- Supports structured output
Cheaper overall
GPT-4o-mini
$0.15 + $0.60 /1M
Larger context
GPT-4o-mini
131K
More providers
GPT-4o-mini
6 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| GPT-4 | GPT-4o-mini | |
|---|---|---|
| Input $/1M | $30.00via OpenAI | $0.15via OpenAI best |
| Output $/1M | $60.00via OpenAI | $0.60via OpenAI best |
| Context window | 8K | 131K best |
| Max output | 4K | 16K best |
| Serving providers | 3 | 6 best |
| Date | Released Nov 6, 2023 | Released Jul 18, 2024 |
Benchmarks
Benchmark scores, side by side| GPT-4 | GPT-4o-mini | |
|---|---|---|
| Intelligence | 6.7 | 6.7 |
| Terminal-Bench | Not available | 6% |
| GPQA Diamond | 35% | 43% best |
| Output speed | Not available | 120 t/s |
| Latency (TTFT) | Not available | 0.84s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
GPT-4
via Azure
$210
GPT-4o-mini
via Gmi
$1.35
Capabilities
feature support, side by side| Feature | GPT-4 | GPT-4o-mini |
|---|---|---|
| Vision | — | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | — | — |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | — | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, GPT-4 or GPT-4o-mini?
GPT-4o-mini is cheaper for input ($30.00 vs $0.15 per 1M tokens) from OpenAI. GPT-4o-mini is cheaper for output ($60.00 vs $0.60 per 1M tokens) from OpenAI.
What is the context window difference between GPT-4 and GPT-4o-mini?
GPT-4 has a 8K-token context window and GPT-4o-mini has 131K tokens, so GPT-4o-mini can take a larger prompt.
How do GPT-4 and GPT-4o-mini compare on benchmarks?
On the tracked benchmarks, they score about the same on intelligence.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI