Skip to content
Compare

The Kimi K3 API, 40% under list.

Use Kimi K3 for coding, image understanding, and long documents. Base pricing is $1.80 per million input tokens and $9 per million output tokens. K2.7 Code remains available in standard and fast variants.

Per 1M tokensProvider listDraftworks BaseDraftworks Scale
Kimi K3kimi-k3
Input$3.00$1.80$1.80
Cached input$0.30$0.18$0.18
Output$15.00$9.00$9.00
Kimi K2.7 Codekimi-k2.7-code
Input$0.95$0.57$0.57
Cached input$0.19$0.114$0.114
Output$4.00$2.40$2.40
Kimi K2.7 Code Fastkimi-k2.7-code-fast
Input$1.05$0.63$0.63
Cached input$0.18$0.108$0.108
Output$4.40$2.64$2.64

List is the published provider price for each deployment class. Base applies from your first dollar; Scale applies permanently at $5,000 lifetime purchases. The same discount covers every model in the catalog.

Common questions.

How much does Kimi K3 cost on Draftworks?
Kimi K3 costs $1.80 per million input tokens, $0.18 for cached input, and $9 for output on Base. The same 40% discount applies on both Base and Scale. The table also includes both K2.7 Code variants.
What is the difference between standard and fast mode?
Both serve the same K2.7 Code weights. The fast deployment runs on a serving stack tuned for interactive latency and costs about 10% more; the standard deployment is the cheaper default for batch and background work.
Is this the real Kimi K2.7 Code?
Yes. K2.7 Code is an open-weights model served from Azure, responses report the model id, and every response carries an Ed25519-signed receipt over the model id, token counts, and hashes of the exact bytes in and out.
Which endpoint does Kimi use?
POST /v1/chat/completions with the standard OpenAI request shape, including streaming and tool calls. Kimi K3 supports about one million tokens of context; K2.7 Code supports 256K.
Do I need a Moonshot AI account?
No. One Draftworks API key covers Kimi alongside GPT-6 Astra, Claude, Grok 4.6, and GLM 5.3, billed from one prepaid credit balance.

Try Kimi K3.Start with $5.