Venice
AI inference provider · 70 models listed · wins best price on 0.
Models listed
70
across our index
Best price wins
0
0% of models
Avg input
$2.05
USD / 1M tokens
Avg output
$10.65
USD / 1M tokens
All models at Venice
Model
IQ
In/1M
Out/1M
Status
Qwen 3.5 9B
—
$0.050
$0.150
GPT OSS 20B
—
$0.050
$0.190
Qwen 2.5 7B
—
$0.050
$0.130
OpenAI GPT OSS 120B
—
$0.070
$0.300
NVIDIA Nemotron 3 Nano 30B
—
$0.075
$0.300
Mistral Small 3.2 24B Instruct
—
$0.094
$0.250
Google Gemma 3 27B Instruct
—
$0.120
$0.200
GLM 4.7 Flash
—
$0.125
$0.500
GLM 4.7 Flash
—
$0.130
$0.550
GPT OSS 120B
—
$0.130
$0.650
GLM 4.7 Flash Heretic
—
$0.140
$0.800
Nvidia Nemotron Cascade 2 30b A3b
—
$0.140
$0.800
Gemma 3 27B
—
$0.140
$0.500
Qwen 3 235B A22B Instruct 2507
—
$0.150
$0.750
Llama 3.2 3B
—
$0.150
$0.600
Google Gemma 4 26b A4b It
—
$0.163
$0.500
Google Gemma 4 31b It
—
$0.175
$0.500
Mistral Small 2603
—
$0.188
$0.750
GPT-4o Mini
—
$0.188
$0.750
Qwen3 30B A3B
—
$0.190
$0.690
Venice Uncensored 1.1
—
$0.200
$0.900
Venice Uncensored 1 2
—
$0.200
$0.900
Grok 4.1 Fast
38.6
$0.230
$0.570
Qwen3 VL 235B
—
$0.250
$1.50
Venice Uncensored 1.1
—
$0.250
$1.15
Qwen3 VL 30B A3B
—
$0.250
$0.900
Qwen 3.5 35B A3B
—
$0.313
$1.25
Arcee Trinity Large Thinking
—
$0.313
$1.13
Mercury 2
—
$0.313
$0.938
DeepSeek V3.2
41.7
$0.330
$0.480
MiniMax M2.5
41.9
$0.340
$1.19
Qwen 3 Next 80b
—
$0.350
$1.90
Qwen 3 Coder 480B Turbo
—
$0.350
$1.50
MiniMax M2.7
49.6
$0.375
$1.50
Qwen 3 235B A22B Thinking 2507
—
$0.450
$3.50
Venice Role Play Uncensored
—
$0.500
$2.00
Qwen3.5 122B A10B
—
$0.500
$4.00
GLM 4.7
—
$0.550
$2.65
Kimi K2.5
46.8
$0.560
$3.50
Qwen 3 6 Plus
50.0
$0.625
$3.75
Gemini 3 Flash Preview
46.4
$0.700
$3.75
Llama 3.3 70B
36.0
$0.700
$2.80
Qwen3 5 397b A17b
—
$0.750
$4.50
Qwen 3 Coder 480b
24.8
$0.750
$3.00
Kimi K2 Thinking
46.8
$0.750
$3.20
GLM 4.6
—
$0.850
$2.75
Openai Gpt 54 Mini
—
$0.938
$5.63
GLM 5
40.6
$1.00
$3.20
Aion Labs Aion 2 0
—
$1.00
$2.00
Hermes 3 Llama 3.1 405b
—
$1.10
$3.00
GLM 4.7
—
$1.10
$4.15
GLM 5
—
$1.10
$4.15
Z Ai Glm 5 Turbo
—
$1.20
$4.00
Z Ai Glm 5v Turbo
—
$1.50
$5.00
Zai Org Glm 5 1
51.4
$1.75
$5.50
GPT-5.2
44.6
$2.19
$17.50
GPT-5.2 Codex
44.6
$2.19
$17.50
GPT-5.3 Codex
53.6
$2.19
$17.50
Grok 4 20
38.6
$2.27
$6.80
Grok 4 20 Multi Agent
—
$2.27
$6.80
Gemini 3.1 Pro Preview
57.2
$2.50
$15.00
GPT-4o
—
$3.13
$12.50
GPT-5.4
56.8
$3.13
$18.80
Claude Sonnet 4.6
51.7
$3.60
$18.00
Claude Sonnet 4.5
—
$3.75
$18.75
Claude Opus 4 7
—
$6.00
$30.00
Claude Opus 4.6
53.0
$6.00
$30.00
Claude Opus 4.5
—
$6.00
$30.00
Claude Opus 4.6 Fast
—
$36.00
$180.00
GPT-5.4 Pro
—
$37.50
$225.00
Cite: Venice pricing data
Citation
Venice — AI inference pricing (70 models). Inference Index, 2026-04-16. https://inferenceindex.ai/providers/veniceAPI
curl https://inferenceindex.ai/api/prices