| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| venice | 1M | $0.0966 | $0.1925 | $0.0196 | — | 100.00% | |
| venice | 1M | $0.13 | $0.26 | $0.028 | — | 100.00% | |
| venice | 1M | $1.65 | $3.301 | $0.33 | — | 98.17% | |
| venice | 1M | $1.65 | $4.95 | $0.165 | — | 98.65% | |
| venice/fp8 | 1M | $0.30 | $1.20 | $0.0075 | — | 99.29% | |
| venice/fp8 | 1M | $0.30 | $1.20 | $0.0075 | — | 100.00% | |
| venice/fp4 | 198K | $0.43 | $1.75 | $0.08 | — | 99.74% | |
| venice/fp4 | 198K | $0.4004 | $1.9292 | $0.0801 | — | 100.00% | |
| venice/fp8 | 198K | $1.00 | $3.20 | $0.20 | — | 98.54% | |
| venice/turbo | 200K | $1.20 | $4.00 | $0.24 | — | 100.00% | |
| venice/fp8 | 200K | $1.4014 | $4.4044 | $0.2603 | — | 99.64% | |
| venice/fp8 | 1M | $1.40 | $4.40 | $0.26 | — | 99.64% | |
| venice | 1M | $1.40 | $4.40 | $0.26 | — | 98.90% | |
| venice | 1M | $0.15 | $0.50 | $0.03 | — | 99.58% | |
| venice/bf16 | 256K | $0.13 | $0.40 | $0.05 | — | 100.00% | |
| venice/fp4 | 256K | $0.12 | $0.36 | $0.09 | — | 100.00% | |
| venice | 256K | $0.532 | $3.325 | $0.209 | — | 100.00% | |
| venice/int4 | 256K | $0.75 | $3.50 | $0.16 | — | 93.75% | |
| venice/int4 | 256K | $0.75 | $3.50 | $0.16 | — | 100.00% | |
| venice/fp8 | 1M | $0.40 | $2.00 | $0.08 | — | 99.79% | |
| venice/fp8 | 1M | $0.175 | $0.35 | $0.00375 | — | 87.47% | |
| venice | 198K | $0.27 | $0.95 | $0.03 | — | 95.28% | |
| venice/fp8 | 524K | $0.30 | $1.20 | $0.06 | — | 93.03% | |
| venice/fp8 | 256K | $0.0938 | $0.25 | — | — | 98.61% | |
| venice/fp8 | 256K | $0.625 | $3.125 | $0.1875 | — | 99.85% | |
| venice/fp4 | 262K | $0.20 | $0.50 | $0.04 | — | 99.18% | |
| venice/fp8 | 128K | $0.15 | $0.75 | — | — | 99.92% | |
| venice/fp8 | 128K | $0.45 | $3.50 | — | — | 100.00% | |
| venice/fp8 | 256K | $0.35 | $1.50 | $0.04 | — | 93.86% | |
| venice/fp8 | 128K | $0.21 | $1.90 | $0.10 | — | 98.56% | |
| venice | 128K | $0.75 | $4.50 | — | — | 97.26% | |
| venice | 256K | $0.15 | $1.00 | $0.05 | — | 99.77% | |
| venice/fp8 | 256K | $0.325 | $3.25 | — | — | 99.20% | |
| venice/fp8 | 256K | $0.10 | $1.00 | — | — | 99.65% | |
| venice | 262K | $2.00 | $6.00 | $0.25 | — | 93.48% | |
| venice/fp8 | 262K | $0.45 | $3.20 | — | — | 99.74% | |
| Uncensored | venice/fp16 | 128K | $0.20 | $0.90 | — | — | 100.00% |
| venice/int4 | 128K | $0.03 | $0.15 | $0.03 | — | 100.00% |
