Kimi K2.7 Code vs Mercury 2
API pricing, context window and capabilities for Kimi K2.7 Code 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 numbersKimi K2.7 Code wins on Terminal-Bench, on intelligence and on context window. Mercury 2 wins on price.
Price
Mercury 2
Terminal-Bench
Kimi K2.7 Code
Intelligence
Kimi K2.7 Code
Context window
Kimi K2.7 Code
Key takeaways
who wins on what, from the published numbersKimi K2.7 Code wins
- Larger context window (262K vs 128K)
- Higher max output (262K vs 50K)
- More serving providers (16 vs 3)
- Supports vision
- Has reasoning mode
Mercury 2 wins
- Cheaper input ($0.671 vs $0.25 /1M)
- Cheaper output ($3.35 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
Kimi K2.7 Code
262K
More providers
Kimi K2.7 Code
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. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
| Kimi K2.7 Code | Mercury 2 | |
|---|---|---|
| Input $/1M | $0.671OpenRouter routed quote | $0.25via Inception best |
| Output $/1M | $3.35OpenRouter routed quote | $0.75via Inception best |
| Context window | 262K best | 128K |
| Max output | 262K best | 50K |
| Serving providers | 16 best | 3 |
| Date | Released Jun 13, 2026 | Released Feb 24, 2026 |
Benchmarks
Benchmark scores, side by side| Kimi K2.7 Code | Mercury 2 | |
|---|---|---|
| Intelligence | 25.8 best | 13.8 |
| Terminal-Bench | 67% best | 27% |
| GPQA Diamond | 90% best | 77% |
| Output speed | 64 t/s | 554 t/s best |
| Latency (TTFT) | 2.75s best | 6.83s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Kimi K2.7 Code
via OpenRouter
$6.71
Mercury 2
via Inception
$2.00
Capabilities
feature support, side by side| Feature | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| Vision | ✓ | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | — |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, Kimi K2.7 Code or Mercury 2?
Mercury 2 is cheaper for input ($0.671 vs $0.25 per 1M tokens) from Inception. Mercury 2 is cheaper for output ($3.35 vs $0.75 per 1M tokens) from Inception.
What is the context window difference between Kimi K2.7 Code and Mercury 2?
Kimi K2.7 Code has a 262K-token context window and Mercury 2 has 128K tokens, so Kimi K2.7 Code can take a larger prompt.
How do Kimi K2.7 Code and Mercury 2 compare on benchmarks?
On the tracked benchmarks, Kimi K2.7 Code leads on Terminal-Bench, and Kimi K2.7 Code 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