Kimi

Kimi K2.6

AI model by Kimi. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.95
Output$4.00
Blended (3:1)$1.71

Source: Artificial Analysis

Performance

Output Speed0 tok/s
Time to First Token0ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Kimi K2.6 is positioned in the mid-tier at $4.00/M output tokens. The benchmark profile is balanced — strongest on GPQA Diamond (91.1%) — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.

Latency. On latency, Kimi K2.6 reports 0 tok/s output speed and 0ms 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 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 2026-07-25.

Compare with similar models

ModelInputOutputSpeed
Kimi K2.6Current
$0.95$4.000 tok/s
DeepSeek R1 0528 (May '25)
$1.35$4.200 tok/s
Qwen3 14B (Reasoning)
$0.35$4.200 tok/s
Muse Spark 1.1 (xhigh)
$1.25$4.25124 tok/s
GLM-5.2 (Non-reasoning)
$1.35$4.2586 tok/s
Qwen3.6 27B (Non-reasoning)
$0.60$3.6057 tok/s

Example Costs

Single Request
$0.0029
1.0K in / 500 out
1K Requests/day
$2.95
1.0M in / 500.0K out
10K Requests/day
$29.50
10.0M in / 5.0M out