Model scorecard
Moonshot kimi-k2-thinking
Composite 64.7/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+64.7/100moonshot/kimi-k2-thinkingtext · 256k context
Capability
eval compositeQuality (blended eval)88
Category: reasoning
Usable context13
256k advertised window
Serving
gateway measuredThroughput23
82 output tokens/s median
Time to first token40
360ms p50
Economics
at provider costPrice efficiency64
$3.00 per 1M output tokens
Quality per dollar88
llmcloud adds $0 to these token prices.
Suggested usage
Not a default pick today. It is a reasonable explicit choice when you need this vendor specifically, or as a failover target inside auto:reasoning.
→ Full workload matrix