GPT-4o vs gpt-oss-120b
API pricing, context window and capabilities for GPT-4o and gpt-oss-120b, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersgpt-oss-120b wins on price and on intelligence. Benchmark data is unavailable for one or both models.
Price
gpt-oss-120b
Terminal-Bench
Not called
Intelligence
gpt-oss-120b
Context window
Tied
Key takeaways
who wins on what, from the published numbersGPT-4o wins
- Supports vision
- Supports audio
gpt-oss-120b wins
- Cheaper input ($2.50 vs $0.03 /1M)
- Cheaper output ($10.00 vs $0.17 /1M)
- Higher max output (16K vs 131K)
- More serving providers (6 vs 23)
- Has reasoning mode
- Has web search
Cheaper overall
gpt-oss-120b
$0.03 + $0.17 /1M
Larger context
Tied
More providers
gpt-oss-120b
23 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-4o | gpt-oss-120b | |
|---|---|---|
| Input $/1M | $2.50via OpenAI | $0.03via Wandb best |
| Output $/1M | $10.00via OpenAI | $0.17via DeepInfra best |
| Context window | 131K | 131K |
| Max output | 16K | 131K best |
| Serving providers | 6 | 23 best |
| Date | Released May 13, 2024 | Released Aug 5, 2025 |
Benchmarks
Benchmark scores, side by side| GPT-4o | gpt-oss-120b | |
|---|---|---|
| Intelligence | 8.4 | 11.6 best |
| Terminal-Bench | Not available | 26% |
| GPQA Diamond | 54% | 78% best |
| Output speed | 150 t/s | 232 t/s best |
| Latency (TTFT) | 0.79s best | 0.83s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
GPT-4o
via Gmi
$23
gpt-oss-120b
via Wandb
$0.32
Capabilities
feature support, side by side| Feature | GPT-4o | gpt-oss-120b |
|---|---|---|
| Vision | ✓ | — |
| Tool use | ✓ | ✓ |
| Reasoning | — | ✓ |
| Audio | ✓ | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, GPT-4o or gpt-oss-120b?
gpt-oss-120b is cheaper for input ($2.50 vs $0.03 per 1M tokens) from Wandb. gpt-oss-120b is cheaper for output ($10.00 vs $0.17 per 1M tokens) from DeepInfra.
What is the context window difference between GPT-4o and gpt-oss-120b?
Both GPT-4o and gpt-oss-120b have about a 131K-token context window.
How do GPT-4o and gpt-oss-120b compare on benchmarks?
On the tracked benchmarks, gpt-oss-120b 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