AI model comparison
GPT-5.6 Luna Pro 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-5.6 Luna Pro
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
- Input / 1M
- $0.20
- Output / 1M
- $1.20
- Context
- 1.05M
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
- $0.15
- Output / 1M
- $0.60
- 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
1.7x cheaper for a typical chat
Higher intelligence score
Tie
Not enough benchmark data
Larger context window
GPT-5.6 Luna Pro
1.05M vs 131K tokens
Newer release
GPT-5.6 Luna Pro
Released July 9, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-5.6 Luna ProNot availablegpt-oss-120b11.6Coding index
GPT-5.6 Luna ProNot availablegpt-oss-120b30.4Agentic index
GPT-5.6 Luna ProNot availablegpt-oss-120b3.7Pricing
GPT-5.6 Luna Pro vs gpt-oss-120b API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-5.6 Luna Pro | gpt-oss-120b |
|---|---|---|
| Input tokensPer 1M tokens | $0.20 | $0.15 |
| Output tokensPer 1M tokens | $1.20 | $0.60 |
| Cached input (read)Per 1M tokens | $0.02 | $0.08 |
| Cache writePer 1M tokens | $0.25 | Not available |
| Long-context pricingPer 1M tokens, for very long prompts | $0.40 in / $1.80 out above 272K | Same rate at any length |
| 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-5.6 Luna Pro$1gpt-oss-120b$0.60Coding task
30K in, 4K out
GPT-5.6 Luna Pro$10.80$5.40 cachedgpt-oss-120b$6.90$4.65 cachedLong document summary
150K in, 2K out
GPT-5.6 Luna Pro$32.40$5.40 cachedgpt-oss-120b$23.70$12.45 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-5.6 Luna Pro | gpt-oss-120b |
|---|---|---|
| Context window | 1.05M tokens | 131K tokens |
| Max output | 128K tokens | 66K tokens |
| Input types | File, Image, Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Max, Extra high, High, Medium, Low, None | High, Medium, Low |
| Default reasoning effort | Medium | Medium |
| Release date | July 9, 2026 | August 5, 2025 |
Features
Supported features
API features available for each model.
| Metric | GPT-5.6 Luna Pro | 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-oss-120bView full model details- gpt-oss-120b vs Gemini 2.5 Flash Lite
- gpt-oss-120b vs Gemma 4 31B
- gpt-oss-120b vs GPT-6 Luna Pro
- gpt-oss-120b vs gpt-oss-20b
- gpt-oss-120b vs GPT-4o-mini
- gpt-oss-120b vs GPT-5 Nano
- gpt-oss-120b vs GPT-4.1 Mini
- gpt-oss-120b vs Qwen3 235B A22B Instruct 2507
- gpt-oss-120b vs DeepSeek V3.1
- gpt-oss-120b vs Mercury 2.5
- gpt-oss-120b vs Nemotron 3.5 Lightning
- gpt-oss-120b vs DeepSeek V3 0324
- gpt-oss-120b vs GPT-4.1 Nano
- gpt-oss-120b vs Llama 4 Maverick
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs Qwen3 Coder 480B A35B
- gpt-oss-120b vs GLM 4.7 Flash
- gpt-oss-120b vs Llama 4 Scout
- gpt-oss-120b vs GLM 4.5 Air
- gpt-oss-120b vs Nemotron 3 Super
- gpt-oss-120b vs Mistral Small 4
- gpt-oss-120b vs Mercury 2
- gpt-oss-120b vs o3 Mini
- gpt-oss-120b vs MiniMax M1
- gpt-oss-120b vs GLM 4.6V
- gpt-oss-120b vs Qwen3 Next 80B A3B Thinking
- gpt-oss-120b vs o3 Mini High
- gpt-oss-120b vs Trinity Large Thinking
- gpt-oss-120b vs Solar Pro 3
- gpt-oss-120b vs GPT-3.5 Turbo
Our take
gpt-oss-120b is 1.7x cheaper for a typical chat. GPT-5.6 Luna Pro has the larger context window (1.05M 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-5.6 Luna Pro 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 $0.15 per 1M input tokens and $0.60 per 1M output tokens, while GPT-5.6 Luna Pro costs $0.20 per 1M input tokens and $1.20 per 1M output tokens.
Which has a bigger context window, GPT-5.6 Luna Pro or gpt-oss-120b?
GPT-5.6 Luna Pro supports up to 1.05M tokens of context, compared with 131K for gpt-oss-120b.
Can I use GPT-5.6 Luna Pro and gpt-oss-120b at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-5.6 Luna Pro and gpt-oss-120b answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-5.6 Luna Pro and gpt-oss-120b at the same time. Compare the answers side by side and keep the best one.