GPT-6 Luna vs GPT-oss-120b
API price, context window, capabilities and live speed, side by side.
GPT-6 Luna is about 1.3× cheaper than GPT-oss-120b at a typical 3:1 input-to-output token mix. GPT-6 Luna has the larger context window (1.1M vs 131K tokens). Only GPT-6 Luna supports reasoning; GPT-oss-120b does not. Only GPT-6 Luna 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-6 Luna | GPT-oss-120b | |
|---|---|---|
| Lab | OpenAI | OpenAI |
| Model id | gpt-6-luna | gpt-oss-120b |
| Input / 1M tokens | $0.1 | $0.15 |
| Cached input / 1M | $0.0365 | $0.075 |
| Output / 1M tokens | $0.5 | $0.6 |
| Context window | 1.1M | 131K |
| Input | 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-6 Luna $0.35 | GPT-oss-120b $0.47 |
|---|---|---|
| RAG over documents20K in, 800 out | GPT-6 Luna $2.40 | GPT-oss-120b $3.48 |
| Coding agent step40K in (80% cached), 1.5K out | GPT-6 Luna $2.72 | GPT-oss-120b $4.50 |
Use both, with automatic fallback
Same key, same endpoint: change the model id between "gpt-6-luna" 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-6-luna",
"models": ["gpt-oss-120b"],
"messages": [{ "role": "user", "content": "Hello!" }]
}'FAQ
Which is cheaper, GPT-6 Luna or GPT-oss-120b?
GPT-6 Luna: $0.1 in / $0.5 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-6 Luna 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-6-luna" or "gpt-oss-120b".
Which has a bigger context window, GPT-6 Luna or GPT-oss-120b?
GPT-6 Luna: 1,050,000 tokens. GPT-oss-120b: 131,072 tokens.

