Kimi K3 pricing for api generation

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=6000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0990 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 api generation benchmarks. Hover for details.

Cheapest viable option: Claude Haiku 4.5 at $0.0330/call (67% less, 72/100 quality).

What drives api generation cost

Endpoint generation is the most output-heavy code task tracked here: 3K in for the spec, 6K out for handlers, types, validation, and error paths. Output pricing is therefore the whole ballgame, and the gap between a flagship and a mid-tier model at 6K output tokens compounds fast across a large API surface. Generating one resource at a time costs less than one giant multi-resource prompt.

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 3,000/6,000 token split, output accounts for 91% of the $0.0990 per-call cost.

Kimi K3 quality benchmarks for api generation

Benchmark data for api generation 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