Kimi

Kimi K2.5 (Reasoning)

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

Pricing (per 1M tokens)

Input$0.60
Output$3.00
Blended (3:1)$1.20

Source: Artificial Analysis

Performance

Output Speed43 tok/s
Time to First Token2840ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Kimi K2.5 (Reasoning) is a budget-tier option from Kimi at $3.00/M output tokens. Despite the low price, it scores competitively on Coding Index (46.8) and Intelligence Index (36.0) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Kimi K2.5 (Reasoning) reports 43 tok/s output speed and 2840ms 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 K2.5 (Reasoning) costs $0.90 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

ModelInputOutputSpeed
Kimi K2.5 (Reasoning)Current
$0.60$3.0043 tok/s
Qwen3.8 27B (medium)
$0.50$3.0065 tok/s
Gemini 3 Flash Preview (Non-reasoning)
$0.50$3.00195 tok/s
Gemini 3 Flash Preview (Reasoning)
$0.50$3.00189 tok/s
Qwen3.8 27B (low)
$0.50$3.0065 tok/s
Hermes 4 - Llama-3.1 405B (Reasoning)
$1.00$3.0031 tok/s

Example Costs

Single Request
$0.0021
1.0K in / 500 out
1K Requests/day
$2.10
1.0M in / 500.0K out
10K Requests/day
$21.00
10.0M in / 5.0M out