Kimi K2 pricing for meeting notes

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=2000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0156 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 meeting notes benchmarks. Hover for details.

Cheapest viable option: Gemini 3 Flash at $0.0100/call (36% less, 83/100 quality).

What drives meeting notes cost

Transcripts are long and low-density (an hour of conversation is a lot of tokens carrying comparatively little information) while the notes that come back are short. That ratio makes this a strong fit for a fast-tier model plus the batch API: notes rarely need to exist within seconds of the meeting ending, and batch discounts apply to the whole request.

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 8,000/2,000 token split, output accounts for 51% of the $0.0156 per-call cost.

Kimi K2 quality benchmarks for meeting notes

Benchmark data for meeting notes 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