Kimi K2
AI model by Kimi. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Kimi K2 is a budget-tier option from Kimi at $2.30/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Kimi K2 reports 41 tok/s output speed and 1220ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Kimi K2 costs $0.80 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Kimi K2Current | $0.57 | $2.30 | 41 tok/s |
| Qwen3 235B A22B 2507 (Reasoning) | $0.23 | $2.30 | 64 tok/s |
| Qwen3.6 35B A3B (Non-reasoning) | $0.38 | $2.25 | 137 tok/s |
| Qwen3.6 35B A3B (Reasoning) | $0.38 | $2.25 | 119 tok/s |
| Qwen3 Coder 30B A3B Instruct | $0.45 | $2.25 | 91 tok/s |
| GLM-4.6 (Reasoning) | $0.55 | $2.20 | 54 tok/s |