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 |
|---|---|---|---|---|
 Qwen Image 2.0 ProAlibaba | — | $0.10/img from $0.05 at APIMart | +100% | — |
 GLM-5.1Zhipu AI | $1.54/1M | $4.84/1M from $1.44 at APIMart | +10% | — |
 Seedream 4.0ByteDance | — | $0.05/img from $0.003 at Kie.ai | +67% | — |
| GLM-4.7Zhipu AI | $0.55/1M | $2.65/1M from $1.10 at AIHubMix | +20% | — |
| GLM-4.6Zhipu AI | $0.43/1M | $1.75/1M from $1.10 at AIHubMix | -20% | — |
| Ideogram V4Ideogram | — | $0.06/img from $0.018 at Kie.ai | +243% | — |
 Gemma 4Google | $0.12/1M | $0.36/1M from $0.30 at FastRouter | +20% | — |
| Kimi K2.7 Code HighSpeedMoonshot AI | $0.75/1M | $3.50/1M from $2.76 at Kenari | -7% | — |
| Hermes 3 405B InstructNous Research | $1.10/1M | $3/1M from $1 at OpenRouter | +200% | — |
| Recraft V4Recraft | — | $0.05/img from $0.04 at Fal | +25% | — |
 Llama-3.3-70B-InstructMeta | $0.70/1M | $2.80/1M from $0.32 at Deep Infra | +775% | — |
| Qwen3.6 27BAlibaba | $0.325/1M | $3.25/1M from $2 at OpenRouter | -10% | — |
 DeepSeek V4 Flash 0731DeepSeek | $0.13/1M | From$0.26/1M from $0.133 at OpenRouter | +95% | — |
| Grok 4.5xAI | $2.27/1M | $6.80/1M from $3.20 at APIMart | +13% | — |
| Qwen3.5 397B-A17BAlibaba | $0.75/1M | $4.50/1M from $0.986 at AIHubMix | +336% | — |
| Mercury 2Inception | $0.313/1M | $0.938/1M from $0.75 at OpenRouter | +25% | — |
| Qwen3 Coder 480B A35B InstructAlibaba | $0.35/1M | $1.50/1M from $0.95 at Helicone | +58% | — |
| Qwen3.7 MaxAlibaba | $2.70/1M | $8.05/1M from $3.75 at DevPass (LLM Gateway) | +63% | — |
| Qwen3.5 35B-A3BAlibaba | $0.15/1M | $1/1M from $0.451 at AIHubMix | -50% | — |
| Gemma 3 27BGoogle | $0.12/1M | $0.20/1M from $0.16 at Deep Infra | +25% | — |
| Gemma 4 26B A4B ITGoogle | $0.13/1M | $0.40/1M from $0.225 at OpenRouter | -33% | — |
| Qwen3.7 PlusAlibaba | $0.50/1M | $2/1M from $0.30 at CrazyRouter | +82% | — |
| GPT Image 1.5OpenAI | — | $0.26/img | — | — |
 Nemotron 3 Ultra 550B A55BNVIDIA | $0.625/1M | $3.13/1M from $2.20 at Deep Infra | — | — |
 Hunyuan Image 3 InstructTencent | — | $0.09/img from $0.08 at Replicate | +13% | — |
| Recraft V4 ProRecraft | — | $0.29/img from $0.25 at Fal | +16% | — |
| Nemotron 3 Nano 30B A3BNVIDIA | $0.075/1M | $0.30/1M from $0.20 at Novita AI | +50% | — |
 Aion-3.0Aion Labs | $3.75/1M | $7.50/1M from $6 at OpenRouter | +25% | — |
| Aion-3.0-MiniAion Labs | $0.875/1M | $1.75/1M from $1.40 at OpenRouter | +25% | — |
| Claude Opus 4.5 (latest)Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Opus 4.6Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Opus 4.7Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Opus 4.8Anthropic | $5/1M | From$25/1M from $20 at APIMart | ±0% | — |
| Claude Sonnet 4.5 (latest)Anthropic | $3/1M | $15/1M from $12 at APIMart | ±0% | — |
| Deepseek 3.2DeepSeek | $0.33/1M | $0.48/1M from $0.308 at APIMart | +56% | — |
| DeepSeek V4 ProDeepSeek | $1.65/1M | $4.95/1M from $1.58 at CometAPI | +150% | — |
| FLUX.2 [max]Black Forest Labs | — | $0.09/img | — | — |
| Gemini 3 Flash PreviewGoogle | $0.70/1M | $3.75/1M from $1.50 at Vertex | +25% | — |
| Gemini 3.5 FlashGoogle | $1.55/1M | $9.45/1M from $2.70 at Kie.ai | +250% | — |
| Gemini 3.5 Flash LiteGoogle | $0.375/1M | $3.13/1M from $2 at APIMart | +25% | — |
| Gemini 3.6 FlashGoogle | $0.938/1M | $4.69/1M from $3 at CometAPI | +25% | — |
| Gemini 3.7 FlashGoogle | $0.938/1M | $4.69/1M from $1.13 at Kie.ai | +317% | — |
| Gemini Embedding 2 PreviewGoogle | $0.25/1M | $0.25/1M from $0.20 at OrcaRouter | +25% | — |
| Gemini Pro LatestGoogle | $2.50/1M | $15/1M from $6.90 at Kenari | +25% | — |
| GLM 5 TurboZhipu AI | $1.20/1M | $4/1M from $3.19 at ZenMux | +25% | — |
| GLM-5V-TurboZhipu AI | $1.50/1M | $5/1M from $3.10 at AIHubMix | +61% | — |
| GPT-5.5 ProOpenAI | $30/1M | $180/1M from $144 at CometAPI | ±0% | — |
| GPT-5.6 TerraOpenAI | $2/1M | $12/1M from $9.60 at APIMart | ±0% | — |
| Grok 4.20 (Reasoning)xAI | $1.42/1M | $2.83/1M from $2 at APIMart | +13% | — |
| Grok 4.3xAI | $1.42/1M | $2.83/1M from $2 at APIMart | +13% | — |
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