DeepSeek V4 Pro 0423 vs Mercury 2
API pricing, context window and capabilities for DeepSeek V4 Pro 0423 and Mercury 2, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersDeepSeek V4 Pro 0423 wins on Terminal-Bench, on intelligence and on context window. Mercury 2 wins on price.
Price
Mercury 2
Terminal-Bench
DeepSeek V4 Pro 0423
Intelligence
DeepSeek V4 Pro 0423
Context window
DeepSeek V4 Pro 0423
Key takeaways
who wins on what, from the published numbersDeepSeek V4 Pro 0423 wins
- Larger context window (1M vs 128K)
- Higher max output (1M vs 50K)
- More serving providers (16 vs 3)
- Has reasoning mode
Mercury 2 wins
- Cheaper input ($0.435 vs $0.25 /1M)
- Cheaper output ($0.87 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
DeepSeek V4 Pro 0423
1M
More providers
DeepSeek V4 Pro 0423
16 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| DeepSeek V4 Pro 0423 | Mercury 2 | |
|---|---|---|
| Input $/1M | $0.435via Tencent | $0.25via Inception best |
| Output $/1M | $0.87via Tencent | $0.75via Inception best |
| Context window | 1M best | 128K |
| Max output | 1M best | 50K |
| Serving providers | 16 best | 3 |
| Date | Released Apr 24, 2026 | Released Feb 24, 2026 |
Benchmarks
Benchmark scores, side by side| DeepSeek V4 Pro 0423 | Mercury 2 | |
|---|---|---|
| Intelligence | 30.4 best | 13.8 |
| Terminal-Bench | 65% best | 27% |
| GPQA Diamond | 89% best | 77% |
| Output speed | 100 t/s | 554 t/s best |
| Latency (TTFT) | 1.64s best | 6.83s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
DeepSeek V4 Pro 0423
via Tencent
$3.04
Mercury 2
via Inception
$2.00
Capabilities
feature support, side by side| Feature | DeepSeek V4 Pro 0423 | Mercury 2 |
|---|---|---|
| Vision | — | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | — |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro 0423 or Mercury 2?
Mercury 2 is cheaper for input ($0.435 vs $0.25 per 1M tokens) from Inception. Mercury 2 is cheaper for output ($0.87 vs $0.75 per 1M tokens) from Inception.
What is the context window difference between DeepSeek V4 Pro 0423 and Mercury 2?
DeepSeek V4 Pro 0423 has a 1M-token context window and Mercury 2 has 128K tokens, so DeepSeek V4 Pro 0423 can take a larger prompt.
How do DeepSeek V4 Pro 0423 and Mercury 2 compare on benchmarks?
On the tracked benchmarks, DeepSeek V4 Pro 0423 leads on Terminal-Bench, and DeepSeek V4 Pro 0423 leads on intelligence.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI