The Known Good Updated 4 Sep 2026 Subscribe
Providers· Inference host· 10 tracked models

Io Net — pricing & performance

Compare models All providers Data sources
Models served
10
of 1,094 tracked models
Mean output speed
34
tokens per second, averaged over
10 measured endpoints
Mean latency
1.6s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.073
per 1M tokens at a 3:1
input:output blend
Output speed on Io Net

Output tokens per second for all 10 models on Io Net with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 10 of 10 models⇩
92
56
46
36
34
22
21
14
13
9
The Known Good
10 models on Io Net
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.14 $0.28 $0.17 14 2.0s 33k
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.22 $0.49 $0.29 21 1.5s 262k
Mistral: Mistral Nemo Mistral $0.044 $0.16 $0.073 36 0.4s 128k
Qwen: Qwen3.6 27B Alibaba $0.39 $2.89 $1.01 13 2.4s 33k
Qwen: Qwen3.6 35B A3B Alibaba $0.19 $1.19 $0.44 92 0.7s 262k
Qwen: Qwen3.8 27B Alibaba $0.43 $3.06 $1.09 34 1.3s 66k
Xiaomi: MiMo-V2.5 Xiaomi $0.21 $0.32 $0.24 46 1.3s 262k
Z.ai: GLM 5.2 Z.ai $0.68 $3.30 $1.33 56 2.4s 262k
Z.ai: GLM 5.3 Z.ai $1.19 $4.18 $1.94 22 2.6s 262k
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 9 1.4s 262k
The Known Good
Source. Prices, endpoint availability and throughput for Io Net 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.