Kimi-K2-Instruct vs Mercury 2.5
API pricing, benchmark indices and specs — updated 19 October 2026.
inception · B · API-only
Input / 1M
$0.04
Output / 1M
$0.15
AA index
12.3
proprietary · 260K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Kimi-K2-Instruct | Mercury 2.5 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 1,026.5 B | n/a — API-only |
| Architecture | DeepseekV3ForCausalLM | n/a — API-only |
| Context length | 131,072 | 260,000 |
| Licence | other | Proprietary |
| Commercial use | Unknown | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 350,413 | n/a — API-only |
| Downloads all time | 4.5 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2025-07-11 | n/a — API-only |
| API input price / 1M tokens | $0.57 | $0.04 |
| API output price / 1M tokens | $2.30 | $0.15 |
| Est. cost per 1M input + 1M output tokens | $2.87 | $0.19 |
| Cached input / 1M tokens | — | $0.004 |
| AA Intelligence Index | 12.7 | 12.3 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 98,304 | 65,536 |
| API providers | 1 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | No | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Kimi-K2-Instruct
$2.87
Mercury 2.5
$0.19
Mercury 2.5 is 15.1× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-K2-Instruct · fp16 @ 128K ctx
3,596.1 GB / 24 GB