Inference host
Venice
LLM prices per million tokens
venice.ai
- Models
- 31
- Routes
- 31
- Cheapest
- $0.1
- Qwen3.5-9B input
- Batch
- n/a
- not stated
Models on Venice
Qwen3.5-9BVenice, fp8, fp8$0.1 / $0.15+22% vs headline
DeepSeek V4 Flash 0423Venice$0.097 / $0.193+9% vs headline
Mistral Small 3.2 24BVenice, fp8, fp8$0.094 / $0.25+25% vs headline
GLM 4.7 FlashVenice, fp8, fp8$0.06 / $0.4
Gemma 4 31BVenice, fp4, fp4$0.12 / $0.36+18% vs headline
Gemma 4 26B A4BVenice, bf16, bf16$0.13 / $0.4+128% vs headline
DeepSeek V4 Flash 0731Venice$0.175 / $0.35+176% vs headline
GLM 5.3 FlashVenice$0.15 / $0.5+245% vs headline
DeepSeek V3.2Venice$0.268 / $0.39+28% vs headline
Qwen3 235B A22B Instruct 2507Venice, fp8, fp8$0.15 / $0.75+15% vs headline
Qwen3.6 35B A3BVenice, fp8, fp8$0.1 / $1+53% vs headline
Qwen3.5-35B-A3BVenice$0.313 / $1.25+22% vs headline
Qwen3 VL 235B A22B InstructVenice, fp8, fp8$0.21 / $1.9+39% vs headline
Qwen3 Coder 480B A35BVenice, fp8, fp8$0.35 / $1.5+34% vs headline
DeepSeek V4.1 FlashVenice, fp8, fp8$0.375 / $1.5+150% vs headline
GLM 4.6Venice, fp4, fp4$0.43 / $1.75
GLM 4.7Venice, fp4, fp4$0.4 / $1.93+6% vs headline
Qwen3.6 27BVenice, fp8, fp8$0.325 / $3.25+4% vs headline
Qwen3.8 27BVenice, fp8, fp8$0.45 / $3.2+19% vs headline
Qwen3 235B A22B Thinking 2507Venice, fp8, fp8$0.45 / $3.5+62% vs headline
Kimi K2.5Venice$0.532 / $3.33+37% vs headline
Kimi K2.7 CodeVenice, int4, int4$0.75 / $3.5+12% vs headline
Kimi K2.6Venice, int4, int4$0.75 / $3.5+40% vs headline
GLM 5Venice, fp8, fp8$1 / $3.2+67% vs headline
Qwen3.5 397B A17BVenice$0.75 / $4.5+92% vs headline
DeepSeek V4 Pro 0423Venice$1.65 / $3.3+76% vs headline
GLM 5.3Venice$1.4 / $4.4+105% vs headline
GLM 5.2Venice, fp8, fp8$1.4 / $4.4+147% vs headline
GLM 5.1Venice, fp8, fp8$1.4 / $4.4+45% vs headline
DeepSeek V4 Pro 0813Venice$1.65 / $4.95+150% vs headline
Qwen3.8 2.4T A95BVenice$2 / $6
Across fru.devCompany profile
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.