Models

Claude Fable 5.2 vs GPT-oss-120b

API price, context window, capabilities and live speed, side by side.

GPT-oss-120b is about 61× cheaper than Claude Fable 5.2 at a typical 3:1 input-to-output token mix. Claude Fable 5.2 has the larger context window (1M vs 131K tokens). Only Claude Fable 5.2 supports image input; GPT-oss-120b does not. Only Claude Fable 5.2 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.

Claude Fable 5.2GPT-oss-120b
LabAnthropic (Claude)OpenAI
Model idclaude-fable-5.2gpt-oss-120b
Input / 1M tokens$8$0.15
Cached input / 1M$0.2$0.075
Output / 1M tokens$40$0.6
Context window1M131K
Inputtext, image, filetext
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 outClaude Fable 5.2 $28.00GPT-oss-120b $0.47
RAG over documents20K in, 800 outClaude Fable 5.2 $192.00GPT-oss-120b $3.48
Coding agent step40K in (80% cached), 1.5K outClaude Fable 5.2 $130.40GPT-oss-120b $4.50

Use both, with automatic fallback

Same key, same endpoint: change the model id between "claude-fable-5.2" 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": "claude-fable-5.2",
    "models": ["gpt-oss-120b"],
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

FAQ

Which is cheaper, Claude Fable 5.2 or GPT-oss-120b?

Claude Fable 5.2: $8 in / $40 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 Claude Fable 5.2 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 "claude-fable-5.2" or "gpt-oss-120b".

Which has a bigger context window, Claude Fable 5.2 or GPT-oss-120b?

Claude Fable 5.2: 1,000,000 tokens. GPT-oss-120b: 131,072 tokens.

More comparisons