Kimi K3 pricing for math reasoning

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=3000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0495 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 math reasoning benchmarks. Hover for details.

Cheapest viable option: GPT 5.6 Luna at $0.003900/call (92% less, 86/100 quality).

What drives math reasoning cost

Short problems, long solutions. Input is trivial and output is large because the derivation is the answer, so output rate is effectively the only price that matters. Models differ sharply in how much they show their working, which means two models at the same output rate can differ substantially in real cost per problem.

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 1,500/3,000 token split, output accounts for 91% of the $0.0495 per-call cost.

Kimi K3 quality benchmarks for math reasoning

Benchmark data for math reasoning 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