Venice
29 served
Models Venice serves
Venice hosts 29 models in the OpenKey catalog. Prices are Venice’s own list price per 1M input tokens, before our fee.
| Model | Built by | Context | Input /M |
|---|---|---|---|
| DeepSeek V3.2 | DeepSeek | 131K | $0.330 |
| DeepSeek V4 Flash | DeepSeek | 1.0M | $0.138 |
| DeepSeek V4 Pro | DeepSeek | 1.0M | $1.65 |
| Gemma 4 26B A4B | 262K | $0.130 | |
| Gemma 4 31B | 262K | $0.120 | |
| MiniMax M2.5 | MiniMax | 205K | $0.270 |
| MiniMax M3 | MiniMax | 1.0M | $0.300 |
| Mistral Small 4 | Mistral AI | 262K | $0.188 |
| Mistral Small 3.2 24B | Mistral AI | 128K | $0.094 |
| Kimi K2.5 | Moonshot AI | 262K | $0.560 |
| Kimi K2.6 | Moonshot AI | 262K | $0.750 |
| Kimi K2.7 Code | Moonshot AI | 262K | $0.750 |
| Nemotron 3 Ultra | NVIDIA | 1M | $0.625 |
| Qwen3 235B A22B Instruct 2507 | Qwen | 262K | $0.150 |
| Qwen3 235B A22B Thinking 2507 | Qwen | 262K | $0.450 |
| Qwen3 Coder 480B A35B | Qwen | 1.0M | $0.350 |
| Qwen3 VL 235B A22B Instruct | Qwen | 262K | $0.210 |
| Qwen3.5-35B-A3B | Qwen | 262K | $0.312 |
| Qwen3.5 397B A17B | Qwen | 256K | $0.750 |
| Qwen3.5-9B | Qwen | 262K | $0.100 |
| Qwen3.6 27B | Qwen | 262K | $0.325 |
| Qwen3.6 35B A3B | Qwen | 262K | $0.100 |
| MiMo-V2.5 | Xiaomi | 1.0M | $0.140 |
| GLM 4.6 | Z.ai | 203K | $0.430 |
| GLM 4.7 | Z.ai | 203K | $0.550 |
| GLM 4.7 Flash | Z.ai | 203K | $0.125 |
| GLM 5 | Z.ai | 203K | $1.00 |
| GLM 5.1 | Z.ai | 203K | $1.54 |
| GLM 5.2 | Z.ai | 1.0M | $1.40 |
From the OpenRouter catalog, Jul 28, 2026. All providers