Models

Claude Haiku 4-5 vs GPT-oss-120b

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

GPT-oss-120b is about 7.6× cheaper than Claude Haiku 4-5 at a typical 3:1 input-to-output token mix. Claude Haiku 4-5 has the larger context window (200K vs 131K tokens). Only Claude Haiku 4-5 supports image input; GPT-oss-120b does not. Only Claude Haiku 4-5 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 Haiku 4-5GPT-oss-120b
LabAnthropic (Claude)OpenAI
Model idclaude-haiku-4-5gpt-oss-120b
Input / 1M tokens$1$0.15
Cached input / 1M$0.1$0.075
Output / 1M tokens$5$0.6
Context window200K131K
Inputtext, imagetext
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 Haiku 4-5 $3.50GPT-oss-120b $0.47
RAG over documents20K in, 800 outClaude Haiku 4-5 $24.00GPT-oss-120b $3.48
Coding agent step40K in (80% cached), 1.5K outClaude Haiku 4-5 $18.70GPT-oss-120b $4.50

Use both, with automatic fallback

Same key, same endpoint: change the model id between "claude-haiku-4-5" 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-haiku-4-5",
    "models": ["gpt-oss-120b"],
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

FAQ

Which is cheaper, Claude Haiku 4-5 or GPT-oss-120b?

Claude Haiku 4-5: $1 in / $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 Claude Haiku 4-5 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-haiku-4-5" or "gpt-oss-120b".

Which has a bigger context window, Claude Haiku 4-5 or GPT-oss-120b?

Claude Haiku 4-5: 200,000 tokens. GPT-oss-120b: 131,072 tokens.

More comparisons