Mercury 2 vs Qwen3.5 397B A17B
API pricing, context window and capabilities for Mercury 2 and Qwen3.5 397B A17B, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersQwen3.5 397B A17B wins on Terminal-Bench, on intelligence and on context window.
Price
Tied
Terminal-Bench
Qwen3.5 397B A17B
Intelligence
Qwen3.5 397B A17B
Context window
Qwen3.5 397B A17B
Key takeaways
who wins on what, from the published numbersMercury 2 wins
- Cheaper output ($0.75 vs $0.986 /1M)
Qwen3.5 397B A17B wins
- Cheaper input ($0.25 vs $0.164 /1M)
- Larger context window (128K vs 262K)
- Higher max output (50K vs 262K)
- More serving providers (3 vs 7)
- Supports vision
- Has reasoning mode
- Has web search
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
Qwen3.5 397B A17B
262K
More providers
Qwen3.5 397B A17B
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.
| Mercury 2 | Qwen3.5 397B A17B | |
|---|---|---|
| Input $/1M | $0.25via Inception | $0.164via Aihubmix best |
| Output $/1M | $0.75via Inception best | $0.986via Aihubmix |
| Context window | 128K | 262K best |
| Max output | 50K | 262K best |
| Serving providers | 3 | 7 best |
| Date | Released Feb 24, 2026 | Released Feb 16, 2026 |
Benchmarks
Benchmark scores, side by side| Mercury 2 | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence | 13.8 | 18.4 best |
| Terminal-Bench | 27% | 51% best |
| GPQA Diamond | 77% | 89% best |
| Output speed | 554 t/s best | 56 t/s |
| Latency (TTFT) | 6.83s | 2.44s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Mercury 2
via Inception
$2.00
Qwen3.5 397B A17B
via Aihubmix
$1.81
Capabilities
feature support, side by side| Feature | Mercury 2 | Qwen3.5 397B A17B |
|---|---|---|
| Vision | — | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | — | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, Mercury 2 or Qwen3.5 397B A17B?
Qwen3.5 397B A17B is cheaper for input ($0.25 vs $0.164 per 1M tokens) from Aihubmix. Mercury 2 is cheaper for output ($0.75 vs $0.986 per 1M tokens) from Inception.
What is the context window difference between Mercury 2 and Qwen3.5 397B A17B?
Mercury 2 has a 128K-token context window and Qwen3.5 397B A17B has 262K tokens, so Qwen3.5 397B A17B can take a larger prompt.
How do Mercury 2 and Qwen3.5 397B A17B compare on benchmarks?
On the tracked benchmarks, Qwen3.5 397B A17B leads on Terminal-Bench, and Qwen3.5 397B A17B 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