Skip to content
ModelCap

Inference provider

KT: AI models and API pricing

Every tracked model KT serves through OpenRouter, with KT's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Models with a position on a ModelCap board link to their model page, where every provider's deployment is listed side by side.

Snapshot as of 19 November 2026

KT serves 7 tracked models through 7 endpoints as of 19 November 2026; the highest-ranked is Kimi K3 (ModelCap Index #17); mean measured uptime is 98.21%.

Models served
7
On the ModelCap Index
6
Cheapest output price
$0.34/1M

Language models on KT (7)

Ranked models first, in ModelCap Index order. Prices are the lowest KT lists for the model; the endpoint count shows how many deployments carry it.

Language models served by KT, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Kimi K3Moonshot AI#1779.0$0.45$15.001M—87.50%1
2GLM 5.3 FlashZ.ai#2676.4$0.15$0.501M—100.0%1Open weights
3Gemma 4 31BGoogle#4270.7$0.10$0.34262K—100.0%1Open weights
4Motif 3Motif Technologies#8259.9$0.30$1.20262K—100.0%1Open weights
5Solar Pro 4Upstage#14548.0$0.30$1.20524K—100.0%1
6Nemotron 3 UltraNVIDIA#26128.0$0.50$2.20262K—100.0%1
7Mi:dm K 3.0 ProKt—$0.20$0.80262K—100.0%1

KT on ModelCap: common questions

How many AI models does KT serve?

7 tracked models as of 19 November 2026: 7 language models (6 with a public ModelCap Index position), across 7 live endpoints observed through OpenRouter.

What is the best model available on KT?

Kimi K3 from Moonshot AI is the highest-ranked language model KT serves, at ModelCap Index position #17 and $15.00 per 1M output tokens on KT. The table lists every model in Index order.

What is the cheapest model on KT?

Gemma 4 31B at $0.34 per 1M output tokens ($0.10 per 1M input), the lowest positive language-token price KT lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which KT model has the largest context window?

Kimi K3, served with a 1M-token context window on KT. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is KT?

Mean measured uptime across KT endpoints is 98.21% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the KT prices come from?

From the OpenRouter catalogue entry for each KT endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where KT exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 19 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further