Venice AI
Inference hostVenice AI runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.
Models131
- Cheapest for
- 2 models
- Serves
- 3 model types
Visits in September 202620.3M+18.6%Unique visitors 3.7M
- Apr
- May
- Jun
- Jul
- Aug
- Sep
Models by type
Models on Venice AI
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
| Grok-4.20-Multi-AgentxAI | $1.42/1M | $2.83/1M from $2 at APIMart | +13% | — |
 Hy4 previewTencent | $1.04/1M | $3.13/1M from $2.25 at OpenRouter | +39% | — |
 Inkling (256K)Thinking MachinesCheapest | $0.563/1M | $1.50/1M | — | — |
| Kimi K3.1 Pro HighspeedMoonshot AI | $3/1M | $15/1M from $6.13 at Kenari | +59% | — |
| Krea V2krea | — | $0.04/img from $0.03 at Replicate | +33% | — |
| Krea V2 Largekrea | — | $0.07/img from $0.06 at Replicate | +17% | — |
 Llama 3.2 3B InstructMeta | $0.15/1M | $0.60/1M from $0.05 at DevPass (LLM Gateway) | +1100% | — |
 Luma Uni 1Luma AI | — | $0.05/img from $0.04 at Atlas Cloud | +25% | — |
| Luma Uni 1 MaxLuma AI | — | $0.12/img from $0.10 at Atlas Cloud | +20% | — |
 MiniMax-M2.7MiniMax | $0.375/1M | $1.50/1M from $0.60 at EmpirioLabs AI | +150% | — |
 Mistral Small 3.2 24BMistral | $0.094/1M | $0.25/1M from $0.20 at Deep Infra | +25% | — |
| Muse Image 1.0Meta | — | $0.02/img from $0.01 at Vercel AI Gateway | +100% | — |
 Nano Banana 2 LiteGoogle | — | $0.06/img | — | — |
 Nemotron 3.5 Super VL 120B A12BNVIDIA | $0.25/1M | $1.25/1M from $0.50 at Baseten | — | — |
| OpenAI GPT-4o miniOpenAI | $0.15/1M | $0.60/1M from $0.48 at APIMart | ±0% | — |
| OpenAI GPT-5.2OpenAI | $1.75/1M | $14/1M from $11.20 at APIMart | ±0% | — |
| OpenAI GPT-5.3 CodexOpenAI | $1.75/1M | $14/1M from $11.20 at APIMart | +25% | — |
| OpenAI GPT-5.4OpenAI | $2.50/1M | $15/1M from $12 at APIMart | ±0% | — |
| OpenAI GPT-5.4 MiniOpenAI | $0.75/1M | $4.50/1M from $3.60 at APIMart | ±0% | — |
| OpenAI GPT-5.4 ProOpenAI | $30/1M | $180/1M from $144 at APIMart | ±0% | — |
| OpenAI GPT-5.5OpenAI | $5/1M | $30/1M from $24 at APIMart | ±0% | — |
 Qwen ImageAlibaba | — | $0.03/img from $0.02 at FastRouter | +50% | — |
| Qwen3 235B A22B Instruct 2507Alibaba | $0.15/1M | $0.75/1M from $0.10 at Requesty | +650% | — |
| Qwen3 235B A22b Thinking 2507Alibaba | $0.45/1M | $3.50/1M from $2.30 at Hugging Face | +52% | — |
| Qwen3 Next 80B A3B InstructAlibaba | $0.35/1M | $1.90/1M from $1.10 at Deep Infra | +73% | — |
| Qwen3 VL 235B A22B InstructAlibaba | $0.21/1M | $1.90/1M from $0.88 at Deep Infra | +116% | — |
| Qwen3.6 PlusAlibaba | $0.625/1M | $3.75/1M from $1.37 at APIMart | +127% | — |
| Qwen3.8 Max PreviewAlibaba | $2.50/1M | $7.50/1M from $6 at Charm Hyper | +25% | — |
 Seed 2.1 TurboByteDance | $0.625/1M | $3.13/1M from $1.67 at CometAPI | +25% | — |
| Text Embedding 3 LargeOpenAI | $0.163/1M | $0.163/1M from $0.104 at APIMart | +56% | — |
| Text Embedding 3 SmallOpenAI | $0.025/1M | $0.025/1M from $0.016 at APIMart | +56% | — |
Venice AI at a glance
131 models in total: 109 text, 19 image, 3 embedding. The cheapest is Text Embedding 3 Small at $0.025 /1M. GPT-6 Astra has the largest context window, 1.05M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Kimi K3.1 Pro Highspeed (Moonshot AI), released Oct 23, 2026.
Cheapest
- Text Embedding 3 Small$0.025/1M
- Text Embedding 3 Large$0.163/1M
- Gemma 3 27B$0.20/1M
- Gemini Embedding 2 Preview$0.25/1M
- Mistral Small 3.2 24B$0.25/1M
Largest context
- GPT-6 Astra1.05M
- GPT-6.1 Sol1.05M
- GPT-6 Sol1.05M
- GPT-6 Luna1.05M
- GPT-5.6 Luna1.05M
Most searched
- Gemini 4 Argon2M
- Kimi K3658K
- GPT-6 Astra580K
- Muse Wonder569K
- Claude Opus 5.5405K
Newest
- Kimi K3.1 Pro Highspeed (Moonshot AI)Oct 23, 2026
- Kimi K3.1 Pro HighspeedOct 23, 2026
- Mercury 3Oct 19, 2026
DeepSeek V4 Flash Vision ExpOct 17, 2026- MiniMax-M3.1-FlashOct 17, 2026