Kimi K3 pricing for code refactoring

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=4000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0720 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 refactoring benchmarks. Hover for details.

Cheapest viable option: Claude Haiku 4.5 at $0.0240/call (67% less, 72/100 quality).

What drives code refactoring cost

Refactoring sends existing code and gets a rewritten version back, so input and output are roughly symmetric, unusual for a code task. That symmetry means neither rate dominates and total cost tracks the size of the file. The practical lever is scope: refactoring one module per call rather than a whole package keeps you off the long-context pricing tier, where some providers re-rate the entire request.

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 4,000/4,000 token split, output accounts for 83% of the $0.0720 per-call cost.

Kimi K3 quality benchmarks for code refactoring

Benchmark data for code refactoring 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