The Known Good Updated 24 Oct 2026 Subscribe
Providers· Inference host· 14 tracked models

Wafer — pricing & performance

Compare models All providers Data sources
Models served
14
of 1,302 tracked models
Mean output speed
118
tokens per second, averaged over
14 measured endpoints
Mean latency
1.0s
time to first token, averaged over
14 measured endpoints
Cheapest blended
$0.059
per 1M tokens at a 3:1
input:output blend
Output speed on Wafer

Output tokens per second for all 14 models on Wafer with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

⇩
179
175
174
173
168
144
144
103
92
77
76
60
The Known Good
14 models on Wafer
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.40 $0.17 $0.34 76 0.8s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.13 $0.23 $0.15 179 0.4s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.20 $2.40 $1.50 28 5.1s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $0.28 $4.30 $1.29 168 0.4s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.19 $0.65 $0.30 175 0.4s 1.05M
DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek $0.16 $0.50 $0.24 173 0.4s 1.05M
MiniMax: MiniMax M3.1 Flash MiniMax $0.15 $0.60 $0.26 144 0.7s 1.05M
MoonshotAI: Kimi K3 Moonshot AI $0.36 $11.90 $3.25 103 0.6s 1.05M
NVIDIA: Nemotron 3.5 Lightning NVIDIA $0.035 $0.13 $0.059 174 0.7s 262k
Qwen: Qwen3.8 27B Alibaba $0.060 $2.30 $0.62 58 1.6s 262k
Z.ai: GLM 5.1 Z.ai $1.00 $3.20 $1.55 60 1.2s 203k
Z.ai: GLM 5.2 Z.ai $0.034 $7.00 $1.78 144 0.4s 1.05M
Z.ai: GLM 5.3 Z.ai $0.091 $1.61 $0.47 77 0.5s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.074 $0.20 $0.11 92 0.3s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Wafer 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.