Claude 3 Opus vs GPT-4o
API pricing, context window and capabilities for Claude 3 Opus and GPT-4o, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersClaude 3 Opus wins on intelligence and on context window. GPT-4o wins on price. Benchmark data is unavailable for one or both models.
Price
GPT-4o
Terminal-Bench
Not called
Intelligence
Claude 3 Opus
Context window
Claude 3 Opus
Key takeaways
who wins on what, from the published numbersClaude 3 Opus wins
- Larger context window (200K vs 131K)
GPT-4o wins
- Cheaper input ($15.00 vs $2.50 /1M)
- Cheaper output ($75.00 vs $10.00 /1M)
- Higher max output (4K vs 16K)
- More serving providers (2 vs 6)
- Supports audio
- Supports prompt caching
Cheaper overall
GPT-4o
$2.50 + $10.00 /1M
Larger context
Claude 3 Opus
200K
More providers
GPT-4o
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.
| Claude 3 Opus | GPT-4o | |
|---|---|---|
| Input $/1M | $15.00via Vertex AI Anthropic Models | $2.50via OpenAI best |
| Output $/1M | $75.00via Vertex AI Anthropic Models | $10.00via OpenAI best |
| Context window | 200K best | 131K |
| Max output | 4K | 16K best |
| Serving providers | 2 | 6 best |
| Date | Released Mar 4, 2024 | Released May 13, 2024 |
Benchmarks
Benchmark scores, side by side| Claude 3 Opus | GPT-4o | |
|---|---|---|
| Intelligence | 8.7 best | 8.4 |
| GPQA Diamond | 49% | 54% best |
| Output speed | Not available | 150 t/s |
| Latency (TTFT) | Not available | 0.79s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Claude 3 Opus
via Vertex AI Anthropic Models
$150
GPT-4o
via Gmi
$23
Capabilities
feature support, side by side| Feature | Claude 3 Opus | GPT-4o |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | — | — |
| Audio | — | ✓ |
| Prompt caching | — | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, Claude 3 Opus or GPT-4o?
GPT-4o is cheaper for input ($15.00 vs $2.50 per 1M tokens) from OpenAI. GPT-4o is cheaper for output ($75.00 vs $10.00 per 1M tokens) from OpenAI.
What is the context window difference between Claude 3 Opus and GPT-4o?
Claude 3 Opus has a 200K-token context window and GPT-4o has 131K tokens, so Claude 3 Opus can take a larger prompt.
How do Claude 3 Opus and GPT-4o compare on benchmarks?
On the tracked benchmarks, Claude 3 Opus leads 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