The Known Good Updated 12 Oct 2026 Subscribe
Providers· Inference host· 9 tracked models

InferenceNet — pricing & performance

Compare models All providers Data sources
Models served
9
of 1,191 tracked models
Mean output speed
93
tokens per second, averaged over
9 measured endpoints
Mean latency
0.9s
time to first token, averaged over
9 measured endpoints
Cheapest blended
$0.060
per 1M tokens at a 3:1
input:output blend
Output speed on InferenceNet

Output tokens per second for all 9 models on InferenceNet with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 9 of 9 models⇩
281
97
89
86
80
63
61
44
39
The Known Good
9 models on InferenceNet
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.077 $0.55 $0.20 97 0.6s 1.04M
Inference.net: Schematron V2 Small inference-net $0.050 $0.23 $0.095 281 0.9s 128k
Inference.net: Schematron V2 Turbo inference-net $0.030 $0.15 $0.060 39 0.9s 128k
MoonshotAI: Kimi K3 Moonshot AI $0.73 $10.00 $3.05 80 0.9s 250k
Tencent: Hy4 preview Tencent $0.75 $2.25 $1.12 44 1.9s 1.05M
Xiaomi: MiMo-V2.6-Flash Xiaomi $0.12 $0.28 $0.16 63 0.9s 1.05M
Z.ai: GLM 5.2 Z.ai $0.20 $2.40 $0.75 89 0.4s 1.05M
Z.ai: GLM 5.3 Z.ai $0.080 $4.40 $1.16 86 0.9s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.070 $0.050 $0.065 61 0.4s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for InferenceNet 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.