Side-by-side comparison
DeepSeek V3 0324 vs Mercury 2
DeepSeek
DeepSeek V3 0324
🔧 Tools
{} JSON
Input / 1M
$0.2000
Output / 1M
$0.7700
| DeepSeek V3 0324 | Mercury 2 | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 163,840 | 128,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools, json_mode | tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.2000 | 0.2500 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.7700 | 0.7500 |
Frequently asked questions
Which is cheaper, DeepSeek V3 0324 or Mercury 2?
DeepSeek V3 0324 is cheaper than Mercury 2 on a 50/50 input/output blend by about $0.015 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, DeepSeek V3 0324 or Mercury 2?
DeepSeek V3 0324 has the larger context window at 164k tokens versus 128k tokens for Mercury 2. That means DeepSeek V3 0324 can ingest about 1.3x as much text per request.
What is the difference between DeepSeek V3 0324 and Mercury 2?
DeepSeek V3 0324 comes from DeepSeek; Mercury 2 comes from Inception. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.