Kimi K2 pricing for product descriptions

Quick start

Call Kimi K2 with the OpenAI Python SDK pointed at api.moonshot.cn:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.moonshot.cn/v1",
    api_key=os.environ["MOONSHOT_API_KEY"],
)
response = client.chat.completions.create(
    model="kimi-k2",
    max_tokens=1500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.006475 per call at standard rates
# Input:  $0.95/MTok
# Output: $4.00/MTok

How Kimi K2 compares on cost

Per-call cost for all models scoring 50+ on product descriptions benchmarks. Hover for details.

Cheapest viable option: Gemini 3.6 Flash at $0.006000/call (7% less, 76/100 quality).

What drives product descriptions cost

Catalogue-scale generation: modest output per item, multiplied across thousands of SKUs. Per-call price is small and total spend is set by catalogue size, which makes this a batch API workload almost by definition: descriptions are rarely needed within seconds. Shared brand and formatting context belongs in the cached prefix.

For Kimi K2 specifically, that means output tokens cost 4.2x more than input, at $4.00 vs $0.95 per MTok. At this use case’s 500/1,500 token split, output accounts for 93% of the $0.006475 per-call cost.

Kimi K2 quality benchmarks for product descriptions

Benchmark data for product descriptions is pending for Kimi K2. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for Kimi K2. We recommend testing against your own evaluation criteria.

About Kimi K2

Prices from platform.kimi.ai (K2.6, read 2026-10-11). Cache hit: $0.16/MTok input. Batch API at 60% of standard rate. Not yet benchmarked, so never recommended.

Other models from Moonshot (Kimi)

You can compare Kimi K2 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions