Venice
Inference host · 31 models · 31 priced routes · venice.ai
Models on Venice
| Model | In / out per 1M | Vs headline |
|---|---|---|
| Qwen3.5-9B Venice, fp8, fp8 | $0.1 / $0.15+22% vs headline | +22% |
| DeepSeek V4 Flash 0423 Venice | $0.097 / $0.193+97% vs headline | +97% |
| Mistral Small 3.2 24B Venice, fp8, fp8 | $0.094 / $0.25+25% vs headline | +25% |
| GLM 4.7 Flash Venice, fp8, fp8 | $0.06 / $0.4Same vs headline | Same |
| Gemma 4 31B Venice, fp4, fp4 | $0.12 / $0.36+18% vs headline | +18% |
| Gemma 4 26B A4B Venice, bf16, bf16 | $0.13 / $0.4+128% vs headline | +128% |
| DeepSeek V4 Flash 0731 Venice | $0.175 / $0.35+176% vs headline | +176% |
| GLM 5.3 Flash Venice | $0.15 / $0.5+245% vs headline | +245% |
| DeepSeek V3.2 Venice | $0.268 / $0.39+28% vs headline | +28% |
| Qwen3 235B A22B Instruct 2507 Venice, fp8, fp8 | $0.15 / $0.75+15% vs headline | +15% |
| Qwen3.6 35B A3B Venice, fp8, fp8 | $0.1 / $1+53% vs headline | +53% |
| Qwen3.5-35B-A3B Venice | $0.313 / $1.25+22% vs headline | +22% |
| Qwen3 VL 235B A22B Instruct Venice, fp8, fp8 | $0.21 / $1.9+39% vs headline | +39% |
| Qwen3 Coder 480B A35B Venice, fp8, fp8 | $0.35 / $1.5+34% vs headline | +34% |
| DeepSeek V4.1 Flash Venice, fp8, fp8 | $0.375 / $1.5+150% vs headline | +150% |
| GLM 4.6 Venice, fp4, fp4 | $0.43 / $1.75Same vs headline | Same |
| GLM 4.7 Venice, fp4, fp4 | $0.4 / $1.93+6% vs headline | +6% |
| Qwen3.6 27B Venice, fp8, fp8 | $0.325 / $3.25+4% vs headline | +4% |
| Qwen3.8 27B Venice, fp8, fp8 | $0.45 / $3.2+19% vs headline | +19% |
| Qwen3 235B A22B Thinking 2507 Venice, fp8, fp8 | $0.45 / $3.5+62% vs headline | +62% |
About Venice
Across fru.devCompany profile
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.