Venice

Price history

Blended ($/Mtok, 75% input / 25% output) price over time for every model this host serves. Click a legend entry to hide or show its line.

Hosted offerings

ModelVariantInput $/MtokOutput $/MtokConfidence
gpt-oss-120bint4$0.0300$0.15high
Mistral Small 3.2 24Bfp8$0.0938$0.25high
DeepSeek V4 Flash 0731–$0.13$0.26high
DeepSeek V4 Flash–$0.14$0.28high
MiMo-V2.6-Flashfp8$0.18$0.35high
GLM 5.3 Flash–$0.15$0.50high
Nemotron 3.5 Super VLfp4$0.20$0.50high
Qwen3 235B A22B Instruct 2507fp8$0.15$0.75high
Qwen3.6 35B A3Bfp8$0.10$1.00high
Qwen3.5-35B-A3B–$0.15$1.00high
Uncensored–$0.20$0.90high
MiniMax M2.5–$0.27$0.95high
DeepSeek V4.1 Flashfp8$0.30$1.20high
MiniMax M3fp8$0.30$1.20high
DeepSeek V4.1 Flash 1017fp8$0.30$1.20high
Qwen3 VL 235B A22B Instructfp8$0.21$1.90high
Qwen3 Coder 480B A35Bfp8$0.35$1.50high
GLM-4.6fp4$0.43$1.75high
MiMo-V2.5fp8$0.40$2.00high
Qwen3.6 27Bfp8$0.33$3.25high
GLM 4.7fp4$0.55$2.65high
Qwen3.8 27Bfp8$0.45$3.20high
Qwen3-235B-A22Bfp8$0.45$3.50high
Kimi K2.5–$0.56$3.50high
Kimi K2.7 Codeint4$0.75$3.50high
Kimi K2.6int4$0.75$3.50high
GLM 5fp8$1.00$3.20high
Hy4 previewfp4$1.04$3.13high
Qwen3.5 397B A17B–$0.75$4.50high
GLM 5turbo$1.20$4.00high
DeepSeek V4 Pro–$1.65$3.30high
GLM 5.2fp8$1.40$4.40high
GLM 5.1fp8$1.54$4.84high
DeepSeek V4 Pro 0813–$1.65$4.95high
GLM 5.3–$1.75$5.50high
Qwen3.8 2.4T A95B–$2.50$7.50high
DeepSeek V4.1 Flashfp8+ultrafast$3.00$12.00high