Claude Opus 5.5 vs Mercury 2.5
API price, context window, capabilities and live speed, side by side.
Mercury 2.5 is about 119× cheaper than Claude Opus 5.5 at a typical 3:1 input-to-output token mix. Claude Opus 5.5 has the larger context window (1M vs 260K tokens). Only Claude Opus 5.5 supports image input; Mercury 2.5 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 Opus 5.5 | Mercury 2.5 | |
|---|---|---|
| Lab | Anthropic (Claude) | Other |
| Model id | claude-opus-5.5 | mercury-2.5 |
| Input / 1M tokens | $4 | $0.04 |
| Cached input / 1M | $0.384 | $0.004 |
| Output / 1M tokens | $20 | $0.15 |
| Context window | 1M | 260K |
| Input | text, image, file | 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 | Claude Opus 5.5 $14.00 | Mercury 2.5 $0.12 |
|---|---|---|
| RAG over documents20K in, 800 out | Claude Opus 5.5 $96.00 | Mercury 2.5 $0.92 |
| Coding agent step40K in (80% cached), 1.5K out | Claude Opus 5.5 $74.29 | Mercury 2.5 $0.67 |
Use both, with automatic fallback
Same key, same endpoint: change the model id between "claude-opus-5.5" and "mercury-2.5".
curl https://api.ultragpt.pro/v1/chat/completions \
-H "Authorization: Bearer $ULTRAGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5.5",
"models": ["mercury-2.5"],
"messages": [{ "role": "user", "content": "Hello!" }]
}'FAQ
Which is cheaper, Claude Opus 5.5 or Mercury 2.5?
Claude Opus 5.5: $4 in / $20 out per 1M. Mercury 2.5: $0.04 in / $0.15 out per 1M. Prices are in USD and billed per use from your UltraGPT balance.
Can I use Claude Opus 5.5 and Mercury 2.5 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-opus-5.5" or "mercury-2.5".
Which has a bigger context window, Claude Opus 5.5 or Mercury 2.5?
Claude Opus 5.5: 1,000,000 tokens. Mercury 2.5: 260,000 tokens.
