Kimi K2 0711
by Moonshot AIRank #374Score 40.0
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Performance Overview
Score
40.0
Rank
#374
24h Change
0
7d Change
0
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 33.3 | 30% | 10.0 | 2026-09-22T14:24:50.013Z |
Pricing pricing_tier | 97.7 | 25% | 24.4 | 2026-09-22T14:24:50.013Z |
Context Window context_window | 81.2 | 15% | 12.2 | 2026-09-22T14:24:50.013Z |
Recency recency | 53.1 | 15% | 8.0 | 2026-09-22T14:24:50.013Z |
Output Capacity output_capacity | 79.8 | 15% | 12.0 | 2026-09-22T14:24:50.013Z |
Top Drivers
positive
Pricing
$2.30/M output tokens
$2.30
positive
Context Window
131K token context window
131K
positive
Output Capacity
Up to 98K output tokens per request
98K
negative
Capabilities
Supports tools, streaming
2/7
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | No |
| JSON Mode | No |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.57
Output / 1M tokens
$2.30
Context Window
131K
Max Output
98K