Kimi K3 pricing for code review

Quick start

Call Kimi K3 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-k3",
    max_tokens=2000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0450 per call at standard rates
# Input:  $3.00/MTok
# Output: $15.00/MTok

How Kimi K3 compares on cost

Per-call cost for all models scoring 50+ on code review benchmarks. Hover for details.

Cheapest viable option: Claude Sonnet 5 at $0.0300/call (33% less, 96/100 quality).

What drives code review cost

Review is input-heavy in a way generation is not: the diff or file goes in whole, and structured feedback comes back short. That flips the usual optimization: input rate and cache discounts matter more than output rate. Reviewing the same repository repeatedly means the surrounding context is identical call over call, which is exactly the shape prompt caching is designed for.

For Kimi K3 specifically, that means output tokens cost 5.0x more than input, at $15.00 vs $3.00 per MTok. At this use case’s 5,000/2,000 token split, output accounts for 67% of the $0.0450 per-call cost.

Kimi K3 quality benchmarks for code review

Benchmark data for code review is pending for Kimi K3. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for Kimi K3. We recommend testing against your own evaluation criteria.

About Kimi K3

Prices from platform.kimi.ai (read 2026-10-11). Cache hit: $0.30/MTok input. Kimi K3 is a 2.8T-parameter open-weight MoE model. No batch discount published yet. Not yet benchmarked, so never recommended.

Other models from Moonshot (Kimi)

You can compare Kimi K3 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