Kimi K2 0905
AI model by Kimi. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Kimi K2 0905 is a budget-tier option from Kimi at $2.50/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 0905 reports 41 tok/s output speed and 1130ms 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 0905 costs $0.85 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 K2 0905Current | $0.60 | $2.50 | 41 tok/s |
| Nova 2.0 Omni (medium) | $0.30 | $2.50 | — |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | 332 tok/s |
| Nova 2.0 Omni (Non-reasoning) | $0.30 | $2.50 | — |
| Gemini 2.5 Flash (Reasoning) | $0.30 | $2.50 | 225 tok/s |
| Ling-2.6-1T | $0.30 | $2.50 | — |