GPT-5.6 Luna Pro vs GPT-oss-120b
API price, context window, capabilities and live speed, side by side.
GPT-oss-120b is about 1.7× cheaper than GPT-5.6 Luna Pro at a typical 3:1 input-to-output token mix. GPT-5.6 Luna Pro has the larger context window (1.1M vs 131K tokens). Only GPT-5.6 Luna Pro supports image input; GPT-oss-120b does not. Only GPT-5.6 Luna Pro supports tool calling; GPT-oss-120b does not. Both run on the same UltraGPT API key, so you can switch between them by changing the model field - or list both in models: [...] for automatic fallback.
GPT-5.6 Luna Pro | GPT-oss-120b | |
|---|---|---|
| Lab | OpenAI | OpenAI |
| Model id | gpt-5.6-luna-pro | gpt-oss-120b |
| Input / 1M tokens | $0.2 | $0.15 |
| Cached input / 1M | $0.02 | $0.075 |
| Output / 1M tokens | $1.2 | $0.6 |
| Context window | 1.1M | 131K |
| Input | file, image, text | text |
| Output | text | text |
| Tool calling | ✓ | — |
| Vision (image input) | ✓ | — |
| Reasoning | — | — |
Cost of 1,000 requests
Estimated from the list prices above; your real cost is reported per request in usage.cost.
| Chatbot1.5K tokens in, 400 out | GPT-5.6 Luna Pro $0.78 | GPT-oss-120b $0.47 |
|---|---|---|
| RAG over documents20K in, 800 out | GPT-5.6 Luna Pro $4.96 | GPT-oss-120b $3.48 |
| Coding agent step40K in (80% cached), 1.5K out | GPT-5.6 Luna Pro $4.04 | GPT-oss-120b $4.50 |
Use both, with automatic fallback
Same key, same endpoint: change the model id between "gpt-5.6-luna-pro" and "gpt-oss-120b".
curl https://api.ultragpt.pro/v1/chat/completions \
-H "Authorization: Bearer $ULTRAGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-luna-pro",
"models": ["gpt-oss-120b"],
"messages": [{ "role": "user", "content": "Hello!" }]
}'FAQ
Which is cheaper, GPT-5.6 Luna Pro or GPT-oss-120b?
GPT-5.6 Luna Pro: $0.2 in / $1.2 out per 1M. GPT-oss-120b: $0.15 in / $0.6 out per 1M. Prices are in USD and billed per use from your UltraGPT balance.
Can I use GPT-5.6 Luna Pro and GPT-oss-120b with the same API key?
Yes. Both are available through the OpenAI-compatible UltraGPT API at https://api.ultragpt.pro/v1: set model to "gpt-5.6-luna-pro" or "gpt-oss-120b".
Which has a bigger context window, GPT-5.6 Luna Pro or GPT-oss-120b?
GPT-5.6 Luna Pro: 1,050,000 tokens. GPT-oss-120b: 131,072 tokens.

