Moonshot route
kimi-k3
Kimi K3 API pricing.
One OpenAI-compatible route at the vendor list price with 0% markup, billed per token from one prepaid balance. No subscription required.
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Context window
1M
Provider
Moonshot
Workload calculator
Put the token rate into context.
These examples apply the published input and output rates directly. Actual cost follows the exact tokens your client sends and the model returns.
This route is the 31st cheapest of 39 comparable text models and cheaper than 7 on the same key. Its context window ranks 1st of 39.
Short request
$0.045
10K input + 1K output
Agent turn
$0.45
100K input + 10K output
Exact token billing
No request minimum
One model ID change
OpenAI compatible
Cost neighbourhood
Nearby routes, same workload.
Every comparison uses the same 100K-input / 10K-output turn. Changing route is a one-line model ID edit.
Price does not measure task quality. Check Kimi K3 benchmark evidence before optimizing on cost alone. For generation routes, see GPT Image 2.
First request
Route it in one call.
Use any OpenAI SDK or tool. Keep the request shape, point the base URL at RouterPlex, and set the model ID shown here.
Read the quickstartcurl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "kimi-k3","messages": [{"role": "user", "content": "Hello!"}]}'
Route notes
Questions before production traffic.
01How much does the Kimi K3 API cost?+
Through RouterPlex, Kimi K3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens — the vendor list price with 0% markup, billed per token from a prepaid balance you top up from $5. Moonshot prices cache-hit input at $0.30, cache-miss input at $3, and output at $15 per 1M tokens. RouterPlex bills each category at those published rates.
02What does one Kimi K3 agent turn cost?+
A 100K-token input with a 10K-token reply costs about $0.45 on Kimi K3. That makes it the 31st cheapest of 39 comparable text models on RouterPlex, roughly 41.7× the cost of the cheapest option (DeepSeek V4 Flash).
03What is a cheaper alternative to Kimi K3?+
GPT-5.4 from OpenAI is the closest cheaper model on RouterPlex — $0.40 per agent turn against $0.45 for Kimi K3, at $2.50/1M input and $15.00/1M output. Both run on the same key and the same endpoint, so switching is a one-line model ID change.
04Is Kimi K3 cheaper than Claude Opus 4.6?+
Yes. Per agent turn, Kimi K3 costs about $0.45 against $0.75 for Claude Opus 4.6 — 40% less.
05What is the context window of Kimi K3?+
Kimi K3 supports a 1M token context window on RouterPlex, the 1st largest of the 39 models that publish one.
06Can I use Kimi K3 with the OpenAI SDK?+
Yes. RouterPlex serves Kimi K3 through an OpenAI-compatible endpoint at https://api.routerplex.com/v1 — point any OpenAI SDK or tool at that base URL with your RouterPlex key and set model to "kimi-k3".
Provider family
More from Moonshot.
Deploy this route
Put Kimi K3 behind one key.
Top up from $5 with no subscription required.