Home / Models / Moonshot AI / Kimi K3

Kimi K3 pricing and routing profile

Kimi K3 from Moonshot AI lists at $3.00 per million input tokens and $15.00 per million output tokens, with a 1,048,576-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$3.00
Output, per 1M tokens$15.00
Cached input, per 1M$0.30
Context window1.05M
Confidence signalAvailable

Tool callingStructured outputReasoning controlLog probabilities

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$1.95
Chat reply (2,000 in, 400 out)$12.00
Retrieval-augmented answer (8,000 in, 500 out)$31.50

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Yes. 10 of 19 tracked hosts return token log probabilities for Kimi K3, which is the confidence signal Gimbix uses to let a cheaper model answer first.

Who serves Kimi K3

HostInput / output per 1MLog probabilitiesUptime, last 30 min
InferenceNet$1.00 / $9.00no100.0%
Wafer$1.00 / $9.00no99.9%
Sail Research$1.03 / $9.04yes100.0%
Morph$1.50 / $10.50yes100.0%
Makora$2.04 / $12.75yes99.6%
Relace$2.10 / $10.50no99.8%
Phala$2.55 / $12.75yes100.0%
DigitalOcean$2.55 / $12.95yes100.0%
DeepInfra$2.85 / $14.25no100.0%
Chutes$3.00 / $15.00no—
Parasail$3.00 / $15.00yes98.2%
Modal$3.00 / $15.00no99.9%
Together$3.00 / $15.00no99.9%
Fireworks$3.00 / $15.00yes100.0%
BaseTen$3.00 / $15.00no100.0%
Moonshot AI$3.00 / $15.00no99.5%
Fireworks$3.30 / $16.50yes99.9%
Alibaba$3.45 / $17.25yes—
Fireworks$4.50 / $22.50yes—

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below Kimi K3 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
GLM 5.3 Prime$2.80 / $8.8024%
GPT Audio$2.50 / $10.0025%
GPT-4o (2024-11-20)$2.50 / $10.0025%
GPT-4o (2024-08-06)$2.50 / $10.0025%
GPT-4o$2.50 / $10.0025%
Qwen3.8 Max (0902)$2.00 / $6.0047%

Questions

How much does Kimi K3 cost?

Kimi K3 lists at $3.00 per million input tokens and $15.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $12.00 per 1,000 requests.

What is the context window of Kimi K3?

1,048,576 tokens.

Can a cheaper model replace Kimi K3?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Kimi K3 on one half of your requests and make at most three answers worse on the other.