Kimi K2 pricing for json extraction

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=800,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.006050 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 json extraction benchmarks. Hover for details.

Cheapest viable option: Gemini 3 Flash at $0.003900/call (36% 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 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 3,000/800 token split, output accounts for 53% of the $0.006050 per-call cost.

Kimi K2 quality benchmarks for json extraction

Benchmark data for json extraction 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