The Known Good Updated 22 Nov 2026 Subscribe
Providers· Inference host· 7 tracked models

KT — pricing & performance

Compare models All providers Data sources
Models served
7
of 1,313 tracked models
Mean output speed
111
tokens per second, averaged over
7 measured endpoints
Mean latency
1.0s
time to first token, averaged over
7 measured endpoints
Cheapest blended
$0.16
per 1M tokens at a 3:1
input:output blend
Output speed on KT

Output tokens per second for all 7 models on KT with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 7 of 7 models⇩
The Known Good
7 models on KT
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Google: Gemma 4 31B Google $0.10 $0.34 $0.16 121 0.8s 262k
KT: Mi:dm K 3.0 Pro kt $0.20 $0.80 $0.35 194 0.6s 262k
MoonshotAI: Kimi K3 Moonshot AI $0.45 $15.00 $4.09 75 2.5s 1.05M
Motif Technologies: Motif 3 motif-technologies $0.30 $1.20 $0.53 90 0.4s 262k
NVIDIA: Nemotron 3 Ultra NVIDIA $0.50 $2.20 $0.93 103 0.5s 262k
Upstage: Solar Pro 4 Upstage $0.30 $1.20 $0.53 94 0.9s 524k
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 98 1.5s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for KT are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.