The Known Good Updated 24 Oct 2026 Subscribe
Providers· Inference host· 10 tracked models

ModelRun — pricing & performance

Compare models All providers Data sources
Models served
10
of 1,302 tracked models
Mean output speed
135
tokens per second, averaged over
10 measured endpoints
Mean latency
0.4s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
Output speed on ModelRun

Output tokens per second for all 10 models on ModelRun 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⇩
200
179
167
164
161
130
108
103
93
47
The Known Good
10 models on ModelRun
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.17 $0.67 $0.29 130 0.3s 1.05M
Google: Gemma 4 31B Google $0.75 $1.00 $0.81 179 0.2s 262k
MiniMax: MiniMax M3 MiniMax $0.30 $1.30 $0.55 93 0.8s 1.05M
MiniMax: MiniMax M3.1 Flash MiniMax $0.15 $0.60 $0.26 161 0.2s 1.05M
MoonshotAI: Kimi K2.6 Moonshot AI $0.70 $3.40 $1.38 103 0.3s 262k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.85 $3.75 $1.57 167 0.2s 262k
Qwen: Qwen3.8 27B Alibaba $0.20 $2.50 $0.78 200 0.3s 262k
Qwen: Qwen3.8 27B (free) Alibaba $0.000 $0.000 $0.000 47 0.5s 262k
Z.ai: GLM 5.2 Z.ai $2.20 $6.80 $3.35 108 1.1s 164k
Z.ai: GLM 5.3 Z.ai $2.10 $6.60 $3.23 164 0.2s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for ModelRun 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.