Kimi K2.6 (Non-reasoning)
AI model by Kimi. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Kimi K2.6 (Non-reasoning) is positioned in the mid-tier at $4.00/M output tokens. The benchmark profile is balanced — scoring across standard tests — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Kimi K2.6 (Non-reasoning) reports 40 tok/s output speed and 2760ms 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 K2.6 (Non-reasoning) costs $1.35 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 K2.6 (Non-reasoning)Current | $0.95 | $4.00 | 40 tok/s |
| DeepSeek R1 (Jan '25) | $2.00 | $4.00 | — |
| Qwen3 VL 235B A22B (Reasoning) | $0.40 | $4.00 | 57 tok/s |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | $1.32 | $3.96 | 74 tok/s |
| Inkling (xhigh) | $1.00 | $4.05 | 74 tok/s |
| Qwen3 14B (Reasoning) | $0.35 | $4.20 | 59 tok/s |