AI model comparison
GPT-5 Nano vs gpt-oss-120b
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
OpenAI
GPT-5 Nano
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.
- Input / 1M
- $0.05
- Output / 1M
- $0.40
- Context
- 400K
OpenAI
gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
- Input / 1M
- $0.04
- Output / 1M
- $0.17
- Context
- 131K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
gpt-oss-120b
1.9x cheaper for a typical chat
Higher intelligence score
GPT-5 Nano
13 vs 11.6 on Artificial Analysis
Larger context window
GPT-5 Nano
400K vs 131K tokens
Newer release
GPT-5 Nano
Released August 7, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-5 Nano13gpt-oss-120b11.6Coding index
GPT-5 NanoNot availablegpt-oss-120b30.4Agentic index
GPT-5 NanoNot availablegpt-oss-120b3.7Pricing
GPT-5 Nano vs gpt-oss-120b API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-5 Nano | gpt-oss-120b |
|---|---|---|
| Input tokensPer 1M tokens | $0.05 | $0.04 |
| Output tokensPer 1M tokens | $0.40 | $0.17 |
| Cached input (read)Per 1M tokens | $0.01 | Not available |
| Cache writePer 1M tokens | Not available | Not available |
| Web searchPer request | $0.01 | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
GPT-5 Nano$0.30gpt-oss-120b$0.16Coding task
30K in, 4K out
GPT-5 Nano$3.10$1.75 cachedgpt-oss-120b$1.79Long document summary
150K in, 2K out
GPT-5 Nano$8.30$1.55 cachedgpt-oss-120b$5.89Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-5 Nano | gpt-oss-120b |
|---|---|---|
| Context window | 400K tokens | 131K tokens |
| Max output | 128K tokens | 118K tokens |
| Input types | File, Image, Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low, Minimal | High, Medium, Low |
| Default reasoning effort | Medium | Medium |
| Release date | August 7, 2025 | August 5, 2025 |
Features
Supported features
API features available for each model.
| Metric | GPT-5 Nano | gpt-oss-120b |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Not supported | Supported |
| Stop sequences | Not supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
GPT-5 NanoView full model details- GPT-5 Nano vs Gemini 2.5 Flash Lite
- GPT-5 Nano vs GPT-6 Luna Pro
- GPT-5 Nano vs Gemma 4 31B
- GPT-5 Nano vs Gemma 4 26B A4B
- GPT-5 Nano vs gpt-oss-20b
- GPT-5 Nano vs GPT-4o-mini
- GPT-5 Nano vs Qwen3 235B A22B Instruct 2507
- GPT-5 Nano vs DeepSeek V3.1
- GPT-5 Nano vs Mercury 2.5
- GPT-5 Nano vs Qwen3.5-9B
- GPT-5 Nano vs Nemotron 3.5 Lightning
- GPT-5 Nano vs GPT-4.1 Nano
- GPT-5 Nano vs Granite 4.2 8B
- GPT-5 Nano vs GLM 4.7 Flash
- GPT-5 Nano vs DeepSeek V3.2 Exp
- GPT-5 Nano vs Nemotron 3 Super
- GPT-5 Nano vs Mistral Small 4
- GPT-5 Nano vs Step 3.5 Flash
- GPT-5 Nano vs Mercury 2
gpt-oss-120bView full model details- gpt-oss-120b vs Muse Spark 1.3 Contributor
- gpt-oss-120b vs Gemini 2.5 Flash Lite
- gpt-oss-120b vs Gemma 4 31B
- gpt-oss-120b vs Qwen3.7 Flash
- gpt-oss-120b vs gpt-oss-20b
- gpt-oss-120b vs Qwen3 235B A22B Instruct 2507
- gpt-oss-120b vs Mercury 2.5
- gpt-oss-120b vs Qwen3.5-9B
- gpt-oss-120b vs Nemotron 3.5 Lightning
- gpt-oss-120b vs GPT-4.1 Nano
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs Nemotron 3 Super
- gpt-oss-120b vs Mistral Small 4
- gpt-oss-120b vs Qwen3 Coder 30B A3B Instruct
- gpt-oss-120b vs Nemotron 3 Nano 30B A3B
Our take
gpt-oss-120b is 1.9x cheaper for a typical chat. GPT-5 Nano scores higher on the Artificial Analysis Intelligence Index (13 vs 11.6). GPT-5 Nano has the larger context window (400K vs 131K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is GPT-5 Nano or gpt-oss-120b cheaper?
gpt-oss-120b is cheaper for a typical chat (2K input tokens and 500 output tokens). gpt-oss-120b costs $0.04 per 1M input tokens and $0.17 per 1M output tokens, while GPT-5 Nano costs $0.05 per 1M input tokens and $0.40 per 1M output tokens.
Which has a bigger context window, GPT-5 Nano or gpt-oss-120b?
GPT-5 Nano supports up to 400K tokens of context, compared with 131K for gpt-oss-120b.
Is GPT-5 Nano smarter than gpt-oss-120b?
On the Artificial Analysis Intelligence Index, GPT-5 Nano scores 13 and gpt-oss-120b scores 11.6, putting GPT-5 Nano ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use GPT-5 Nano and gpt-oss-120b at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-5 Nano and gpt-oss-120b answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-5 Nano and gpt-oss-120b at the same time. Compare the answers side by side and keep the best one.