The Known Good Updated 4 Sep 2026 Subscribe
Providers· Inference host· 36 tracked models

Venice — pricing & performance

Compare models All providers Data sources
Models served
36
of 1,094 tracked models
Mean output speed
41
tokens per second, averaged over
36 measured endpoints
Mean latency
1.5s
time to first token, averaged over
36 measured endpoints
Cheapest blended
$0.11
per 1M tokens at a 3:1
input:output blend
Output speed on Venice

Output tokens per second for all 36 models on Venice with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

⇩
140
106
95
89
84
82
57
57
56
54
49
45
The Known Good
36 models on Venice
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V3.2 DeepSeek $0.33 $0.48 $0.37 10 1.5s 160k
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.14 $0.28 $0.17 34 1.0s 1.00M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.17 $0.35 $0.22 41 1.0s 1.00M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.65 $3.30 $2.06 49 1.7s 1.00M
Google: Gemma 4 26B A4B Google $0.13 $0.40 $0.20 14 1.0s 256k
Google: Gemma 4 31B Google $0.12 $0.36 $0.18 32 1.1s 256k
MiniMax: MiniMax M2.5 MiniMax $0.27 $0.95 $0.44 34 1.8s 198k
MiniMax: MiniMax M3 MiniMax $0.30 $1.20 $0.53 95 1.3s 524k
Mistral: Mistral Small 3.2 24B Mistral $0.094 $0.25 $0.13 31 0.8s 256k
Mistral: Mistral Small 4 Mistral $0.19 $0.75 $0.33 82 0.6s 256k
MoonshotAI: Kimi K2.5 Moonshot AI $0.53 $3.33 $1.23 106 1.3s 256k
MoonshotAI: Kimi K2.6 Moonshot AI $0.75 $3.50 $1.44 8 2.0s 256k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.75 $3.50 $1.44 56 1.1s 256k
NVIDIA: Nemotron 3 Ultra NVIDIA $0.62 $3.12 $1.25 9 10.9s 256k
NVIDIA: Nemotron 3.5 Lightning NVIDIA $0.10 $0.25 $0.14 5 0.5s 1.00M
Qwen: Qwen3 235B A22B Instruct 2507 Alibaba $0.15 $0.75 $0.30 21 0.7s 128k
Qwen: Qwen3 235B A22B Thinking 2507 Alibaba $0.45 $3.50 $1.21 24 1.2s 128k
Qwen: Qwen3 Coder 480B A35B Alibaba $0.35 $1.50 $0.64 19 1.9s 256k
Qwen: Qwen3 VL 235B A22B Instruct Alibaba $0.21 $1.90 $0.63 17 2.1s 128k
Qwen: Qwen3.5 397B A17B Alibaba $0.75 $4.50 $1.69 36 2.1s 128k
Qwen: Qwen3.5-35B-A3B Alibaba $0.31 $1.25 $0.55 140 0.7s 256k
Qwen: Qwen3.5-9B Alibaba $0.10 $0.15 $0.11 12 1.1s 256k
Qwen: Qwen3.6 27B Alibaba $0.33 $3.25 $1.06 57 0.6s 256k
Qwen: Qwen3.6 35B A3B Alibaba $0.10 $1.00 $0.33 89 1.1s 256k
Qwen: Qwen3.8 2.4T A95B Alibaba $2.50 $7.50 $3.75 17 0.9s 262k
Qwen: Qwen3.8 27B Alibaba $0.45 $3.20 $1.14 84 1.1s 262k
Venice: Uncensored cognitivecomputations $0.20 $0.90 $0.38 54 0.7s 128k
Xiaomi: MiMo-V2.5 Xiaomi $0.14 $0.28 $0.17 44 1.0s 1.00M
Z.ai: GLM 4.6 Z.ai $0.43 $1.75 $0.76 27 0.9s 198k
Z.ai: GLM 4.7 Z.ai $0.55 $2.65 $1.07 31 0.9s 198k
Z.ai: GLM 4.7 Flash Z.ai $0.060 $0.40 $0.14 34 0.8s 128k
Z.ai: GLM 5 Z.ai $1.00 $3.20 $1.55 22 1.2s 198k
Z.ai: GLM 5.1 Z.ai $1.54 $4.84 $2.37 34 1.2s 200k
Z.ai: GLM 5.2 Z.ai $1.40 $4.40 $2.15 45 1.7s 1.00M
Z.ai: GLM 5.3 Z.ai $1.75 $5.50 $2.69 18 2.0s 1.00M
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 57 0.9s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Venice 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.