Kimi K2 0905
by Moonshot AIRank #223Score 52.4
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Performance Overview
Score
52.4
Rank
#223
24h Change
0
7d Change
-63
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 50.0 | 20% | 10.0 | 2026-08-08T12:28:33.695Z |
Benchmarks benchmark | 50.7 | 30% | 15.2 | 2026-08-08T12:28:33.695Z |
Pricing pricing_tier | 97.5 | 15% | 14.6 | 2026-08-08T12:28:33.695Z |
Context Window context_window | 86.0 | 10% | 8.6 | 2026-08-08T12:28:33.695Z |
Recency recency | 71.3 | 15% | 10.7 | 2026-08-08T12:28:33.695Z |
Output Capacity output_capacity | 83.1 | 10% | 8.3 | 2026-08-08T12:28:33.695Z |
Top Drivers
neutral
Benchmarks
positive
Pricing
$2.50/M output tokens
$2.50
positive
Recency
Released over 1 year ago
11mo ago
neutral
Capabilities
Supports tools, JSON mode, streaming
3/7
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | No |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.60
Output / 1M tokens
$2.50
Context Window
262K
Max Output
100K