Gemini 3.5 Flash vs Mercury 2
API pricing, context window and capabilities for Gemini 3.5 Flash 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 numbersGemini 3.5 Flash wins on Terminal-Bench, on intelligence and on context window. Mercury 2 wins on price.
Price
Mercury 2
Terminal-Bench
Gemini 3.5 Flash
Intelligence
Gemini 3.5 Flash
Context window
Gemini 3.5 Flash
Key takeaways
who wins on what, from the published numbersGemini 3.5 Flash wins
- Larger context window (1M vs 128K)
- Higher max output (66K vs 50K)
- More serving providers (7 vs 3)
- Supports vision
- Has reasoning mode
- Supports audio
- Has web search
Mercury 2 wins
- Cheaper input ($1.50 vs $0.25 /1M)
- Cheaper output ($9.00 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
Gemini 3.5 Flash
1M
More providers
Gemini 3.5 Flash
7 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.
| Gemini 3.5 Flash | Mercury 2 | |
|---|---|---|
| Input $/1M | $1.50via Google | $0.25via Inception best |
| Output $/1M | $9.00via Google | $0.75via Inception best |
| Context window | 1M best | 128K |
| Max output | 66K best | 50K |
| Serving providers | 7 best | 3 |
| Date | Released May 22, 2026 | Released Feb 24, 2026 |
Benchmarks
Benchmark scores, side by side| Gemini 3.5 Flash | Mercury 2 | |
|---|---|---|
| Intelligence | 32.6 best | 13.8 |
| Terminal-Bench | 79% best | 27% |
| GPQA Diamond | 92% best | 77% |
| Output speed | 197 t/s | 554 t/s best |
| Latency (TTFT) | 17.14s | 6.83s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Gemini 3.5 Flash
via OpenRouter
$17
Mercury 2
via Inception
$2.00
Capabilities
feature support, side by side| Feature | Gemini 3.5 Flash | Mercury 2 |
|---|---|---|
| Vision | ✓ | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | — |
| Audio | ✓ | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | ✓ | — |
Related comparisons
Frequently asked questions
Which is cheaper, Gemini 3.5 Flash or Mercury 2?
Mercury 2 is cheaper for input ($1.50 vs $0.25 per 1M tokens) from Inception. Mercury 2 is cheaper for output ($9.00 vs $0.75 per 1M tokens) from Inception.
What is the context window difference between Gemini 3.5 Flash and Mercury 2?
Gemini 3.5 Flash has a 1M-token context window and Mercury 2 has 128K tokens, so Gemini 3.5 Flash can take a larger prompt.
How do Gemini 3.5 Flash and Mercury 2 compare on benchmarks?
On the tracked benchmarks, Gemini 3.5 Flash leads on Terminal-Bench, and Gemini 3.5 Flash 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