The Known Good Updated 24 Oct 2026 Subscribe
Providers· Inference host· 31 tracked models

GMICloud — pricing & performance

Compare models All providers Data sources
Models served
31
of 1,302 tracked models
Mean output speed
53
tokens per second, averaged over
27 measured endpoints
Mean latency
2.4s
time to first token, averaged over
27 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
Output speed on GMICloud

Output tokens per second for the 27 of 31 models on GMICloud with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 31, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
120
94
84
74
72
70
66
60
59
52
52
49
The Known Good
31 models on GMICloud
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V3 0324 DeepSeek $0.29 $1.14 $0.50 30 1.8s 128k
DeepSeek: DeepSeek V3.2 DeepSeek $0.21 $0.31 $0.23 46 1.6s 164k
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.091 $0.18 $0.11 49 1.9s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.29 $0.86 $0.43 59 2.1s 1.05M
DeepSeek: DeepSeek V4 Flash Vision Exp DeepSeek $0.44 $1.32 $0.66 72 2.4s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $0.96 $1.91 $1.20 20 3.1s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.06 $3.17 $1.58 45 2.5s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.18 $0.72 $0.32 120 2.1s 1.05M
DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek $0.18 $0.72 $0.32 74 2.3s 1.05M
MiniMax: MiniMax M2.5 MiniMax $0.30 $1.20 $0.53 52 0.9s 197k
MiniMax: MiniMax M2.7 MiniMax $0.21 $0.84 $0.37 38 1.5s 197k
MiniMax: MiniMax M2.7 (free) MiniMax $0.000 $0.000 $0.000 37 2.2s 197k
MiniMax: MiniMax M3 MiniMax $0.24 $0.96 $0.42 60 2.8s 1.05M
MiniMax: MiniMax M3 (free) MiniMax $0.000 $0.000 $0.000 47 2.1s 1.05M
MiniMax: MiniMax M3.1 Flash MiniMax $0.14 $0.57 $0.25 94 2.0s 1.05M
MoonshotAI: Kimi K2.6 Moonshot AI $0.85 $3.60 $1.54 — — 262k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.95 $4.00 $1.71 48 5.0s 262k
MoonshotAI: Kimi K3 Moonshot AI $3.00 $15.00 $6.00 22 3.9s 262k
Qwen: Qwen3 235B A22B Instruct 2507 Alibaba $0.087 $0.35 $0.15 — — 262k
Qwen: Qwen3.5 397B A17B Alibaba $0.60 $3.60 $1.35 39 1.8s 262k
Tencent: Hy3 Tencent $0.14 $0.58 $0.25 47 2.2s 262k
Tencent: Hy3 preview Tencent $0.18 $0.60 $0.28 84 2.3s 262k
Xiaomi: MiMo-V2.5 Xiaomi $0.12 $0.24 $0.15 — — 1.05M
Xiaomi: MiMo-V2.5-Pro Xiaomi $0.30 $0.61 $0.38 — — 1.05M
Xiaomi: MiMo-V2.6-Flash Xiaomi $0.12 $0.24 $0.15 28 4.6s 1.05M
Xiaomi: MiMo-V2.6-Pro Xiaomi $0.43 $0.87 $0.54 44 3.4s 1.05M
Z.ai: GLM 5 Z.ai $0.60 $1.92 $0.93 70 2.3s 203k
Z.ai: GLM 5.1 Z.ai $1.40 $4.40 $2.15 66 1.5s 203k
Z.ai: GLM 5.2 Z.ai $1.40 $4.40 $2.15 46 2.0s 1.05M
Z.ai: GLM 5.3 Z.ai $0.70 $2.20 $1.07 52 2.9s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.075 $0.25 $0.12 49 1.3s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for GMICloud 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.