Models

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 ProGPT-oss-120b
LabOpenAIOpenAI
Model idgpt-5.6-luna-progpt-oss-120b
Input / 1M tokens$0.2$0.15
Cached input / 1M$0.02$0.075
Output / 1M tokens$1.2$0.6
Context window1.1M131K
Inputfile, image, texttext
Outputtexttext
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 outGPT-5.6 Luna Pro $0.78GPT-oss-120b $0.47
RAG over documents20K in, 800 outGPT-5.6 Luna Pro $4.96GPT-oss-120b $3.48
Coding agent step40K in (80% cached), 1.5K outGPT-5.6 Luna Pro $4.04GPT-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.

More comparisons