Kimi K3 pricing for json extraction

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=800,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0210 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 json extraction benchmarks. Hover for details.

Cheapest viable option: Gemini 3 Flash at $0.003900/call (81% less, 86/100 quality).

What drives json extraction cost

Structured JSON output is compact and predictable, so cost is set almost entirely by how much source text you send. The schema itself is identical on every call and belongs in the cached prefix. This is also a task where a smaller model often matches a larger one: the output space is constrained by the schema, which limits how wrong a cheaper model can go.

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 3,000/800 token split, output accounts for 57% of the $0.0210 per-call cost.

Kimi K3 quality benchmarks for json extraction

Benchmark data for json extraction 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