| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| deepinfra/us | 4K | $7.00 | $0.00 | — | — | 100.00% | |
| deepinfra/fp8 | 66K | $0.192 | $0.00 | — | — | 100.00% | |
| deepinfra/fp8 | 25K | $0.019 | $0.00 | — | — | 100.00% | |
| deepinfra/fp4 | 164K | $0.32 | $0.89 | — | — | 97.99% | |
| deepinfra/fp4/flex | 164K | $0.256 | $0.712 | — | — | 97.56% | |
| deepinfra/fp4 | 164K | $0.25 | $0.95 | $0.13 | — | 100.00% | |
| deepinfra/fp4 | 164K | $0.26 | $0.38 | $0.13 | — | 99.86% | |
| deepinfra/fp8 | 1M | $0.09 | $0.18 | $0.018 | — | 100.00% | |
| deepinfra/fp8 | 1M | $0.06 | $0.18 | $0.015 | — | 100.00% | |
| deepinfra/fp8 | 1M | $0.2156 | $0.6468 | $0.00686 | — | 99.37% | |
| deepinfra/fp8 | 1M | $1.30 | $2.60 | $0.10 | — | 99.78% | |
| deepinfra/fp8 | 1M | $1.30 | $2.60 | $0.10 | — | 99.37% | |
| deepinfra/fp8 | 1M | $0.14 | $0.42 | $0.0042 | — | 100.00% | |
| deepinfra/fp8/flex | 1M | $0.112 | $0.336 | $0.00336 | — | 96.49% | |
| deepinfra/fp8/priority | 1M | $0.21 | $0.63 | $0.0063 | — | 100.00% | |
| deepinfra/fp8 | 1M | $0.098 | $0.294 | $0.00294 | — | 100.00% | |
| deepinfra/fp8/flex | 1M | $0.0784 | $0.2352 | $0.002352 | — | 99.65% | |
| deepinfra/fp8/priority | 1M | $0.147 | $0.441 | $0.00441 | — | 100.00% | |
| deepinfra/us | 262K | $0.06 | $0.00 | $0.06 | — | 100.00% | |
| deepinfra/us | 262K | $0.06 | $0.00 | $0.06 | — | 100.00% | |
| deepinfra/us | 131K | $0.04 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 131K | $0.06 | $0.00 | — | — | 100.00% | |
| E5-Base-v2 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% |
| E5-Large-v2 | deepinfra/us | 512 | $0.01 | $0.00 | — | — | 100.00% |
| deepinfra/fp4 | 203K | $0.50 | $2.00 | $0.10 | — | 99.93% | |
| deepinfra/fp4/flex | 203K | $0.40 | $1.60 | $0.08 | — | 100.00% | |
| deepinfra/fp4 | 203K | $0.40 | $1.75 | $0.08 | — | 100.00% | |
| deepinfra/fp4/flex | 203K | $0.32 | $1.40 | $0.064 | — | 100.00% | |
| deepinfra/fp4 | 1M | $0.5625 | $1.80 | $0.105 | — | 99.31% | |
| deepinfra/fp4/flex | 1M | $0.45 | $1.44 | $0.084 | — | 100.00% | |
| deepinfra/fp4 | 1M | $0.5625 | $2.50 | $0.125 | — | 99.15% | |
| deepinfra/fp4 | 1M | $0.15 | $0.50 | $0.03 | — | 100.00% | |
| GTE-Base | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% |
| GTE-Large | deepinfra/us | 512 | $0.01 | $0.00 | — | — | 100.00% |
| deepinfra/bf16 | 131K | $0.05 | $0.15 | — | — | 86.26% | |
| deepinfra/bf16/flex | 131K | $0.04 | $0.12 | — | — | 0.00% | |
| deepinfra/bf16/priority | 131K | $0.075 | $0.225 | — | — | 87.32% | |
| deepinfra/fp8 | 131K | $0.08 | $0.16 | — | — | 98.98% | |
| deepinfra/bf16 | 131K | $0.05 | $0.10 | — | — | 100.00% | |
| deepinfra/fp8 | 262K | $0.07 | $0.34 | — | — | 100.00% | |
| deepinfra/fp8 | 262K | $0.20 | $0.40 | — | — | 100.00% | |
| deepinfra/fp8/flex | 262K | $0.16 | $0.32 | — | — | 100.00% | |
| deepinfra/fp8/priority | 262K | $0.30 | $0.60 | — | — | 99.48% | |
| deepinfra/turbo | 262K | $0.135 | $0.51 | $0.075 | — | 100.00% | |
| deepinfra/bf16 | 131K | $0.06 | $0.25 | $0.015 | — | 99.34% | |
| deepinfra/fp4 | 1M | $0.834 | $2.501 | $0.042 | — | 99.89% | |
| deepinfra/fp8 | 524K | $0.45 | $1.20 | $0.10 | — | 99.76% | |
| deepinfra/fp4 | 262K | $0.75 | $3.50 | $0.15 | — | 96.00% | |
| deepinfra/mxfp4 | 1M | $2.85 | $14.25 | $0.285 | — | 100.00% | |
| deepinfra/bf16 | 1M | $1.90 | $9.50 | $0.19 | — | 100.00% | |
| Kokoro 82M | deepinfra/us | 4K | $0.62 | $0.00 | — | — | 99.54% |
| deepinfra/bf16 | 131K | $0.06 | $0.18 | $0.012 | — | 98.33% | |
| deepinfra/fp16 | 131K | $0.06 | $0.18 | $0.012 | — | 99.93% | |
| Llama 3 8B Lunaris | deepinfra/turbo | 8K | $0.04 | $0.05 | — | — | 100.00% |
| deepinfra/fp8 | 131K | $0.02 | $0.04 | — | — | 98.84% | |
| Llama 3.1 Euryale 70B v2.2 | deepinfra/fp8 | 131K | $0.85 | $0.85 | — | — | 99.75% |
| deepinfra/turbo | 131K | $0.10 | $0.32 | — | — | 99.63% | |
| deepinfra/fp8 | 328K | $0.10 | $0.30 | — | — | 100.00% | |
| deepinfra/fp8/flex | 328K | $0.08 | $0.24 | — | — | 100.00% | |
| deepinfra/fp8/priority | 328K | $0.15 | $0.45 | — | — | 100.00% | |
| deepinfra/bf16 | 164K | $0.18 | $0.18 | — | — | 99.16% | |
| deepinfra/bf16/flex | 164K | $0.144 | $0.144 | — | — | — | |
| deepinfra/bf16/priority | 164K | $0.27 | $0.27 | — | — | 98.79% | |
| deepinfra/fp8 | 1M | $0.14 | $0.28 | $0.0028 | — | 74.44% | |
| deepinfra/fp8 | 1M | $0.387 | $0.783 | $0.00324 | — | 100.00% | |
| deepinfra/fp8 | 524K | $0.28 | $1.10 | $0.056 | — | 97.49% | |
| deepinfra/fp8/flex | 524K | $0.224 | $0.88 | $0.0448 | — | 65.48% | |
| deepinfra/fp8 | 131K | $0.029 | $0.03 | — | — | 100.00% | |
| deepinfra/fp8 | 33K | $0.05 | $0.08 | — | — | 100.00% | |
| deepinfra/fp8 | 128K | $0.075 | $0.20 | — | — | 99.79% | |
| Multilingual-E5-Large | deepinfra/fp32 | 512 | $0.01 | $0.00 | — | — | 100.00% |
| deepinfra/bf16 | 131K | $0.30 | $1.20 | $0.04 | — | 100.00% | |
| deepinfra/bf16 | 262K | $0.075 | $0.40 | — | — | 99.86% | |
| deepinfra/fp4 | 262K | $0.50 | $2.20 | $0.10 | — | 99.77% | |
| deepinfra/fp4/flex | 262K | $0.40 | $1.76 | $0.08 | — | 100.00% | |
| deepinfra/us | — | $3.33 | $0.00 | — | — | 100.00% | |
| deepinfra/bf16 | 131K | $0.20 | $0.20 | — | — | 100.00% | |
| deepinfra/bf16 | 262K | $0.06 | $0.16 | $0.03 | — | 99.66% | |
| deepinfra/fp4 | 262K | $0.15 | $0.50 | $0.02 | — | 99.92% | |
| deepinfra/bf16 | — | $33.30 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 4K | $7.00 | $0.00 | — | — | 100.00% | |
| deepinfra/bf16 | 16K | $0.07 | $0.14 | — | — | 100.00% | |
| deepinfra/bf16/flex | 16K | $0.056 | $0.112 | — | — | — | |
| deepinfra/fp8 | 33K | $0.36 | $0.40 | — | — | 97.95% | |
| deepinfra/fp8 | 41K | $0.12 | $0.24 | — | — | 99.20% | |
| deepinfra/fp8 | 262K | $0.09 | $0.55 | — | — | 99.38% | |
| deepinfra/fp8 | 41K | $0.12 | $0.50 | — | — | 100.00% | |
| deepinfra/fp8 | 41K | $0.08 | $0.28 | — | — | 98.68% | |
| deepinfra/us | — | $3.33 | $0.00 | — | — | 100.00% | |
| deepinfra/us | — | $7.50 | $0.00 | — | — | 99.92% | |
| deepinfra/turbo | 262K | $0.30 | $1.00 | $0.10 | — | 96.26% | |
| deepinfra/us | 33K | $0.02 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 33K | $0.01 | $0.00 | — | — | 99.79% | |
| deepinfra/fp8 | 262K | $0.09 | $1.10 | — | — | 99.38% | |
| deepinfra/fp8/flex | 262K | $0.072 | $0.88 | — | — | 100.00% | |
| deepinfra/fp8/priority | 262K | $0.135 | $1.65 | — | — | 98.63% | |
| deepinfra/fp8 | 262K | $0.20 | $0.88 | $0.11 | — | 99.72% | |
| deepinfra/fp8 | 262K | $0.15 | $0.60 | — | — | 99.23% | |
| deepinfra/fp8 | 262K | $0.45 | $3.00 | $0.22 | — | 99.93% | |
| deepinfra/fp8 | 262K | $0.26 | $2.60 | — | — | 99.42% | |
| deepinfra/fp8 | 262K | $0.14 | $1.00 | $0.05 | — | 99.89% | |
| deepinfra/bf16 | 262K | $0.10 | $0.15 | — | — | 99.92% | |
| deepinfra/fp8 | 262K | $0.32 | $3.20 | — | — | 100.00% | |
| deepinfra/fp8 | 262K | $0.10 | $0.95 | $0.10 | — | 98.88% | |
| deepinfra/bf16 | 262K | $0.15 | $1.875 | $0.0375 | — | 100.00% | |
| deepinfra/fp4 | 164K | $0.50 | $2.15 | $0.35 | — | 99.72% | |
| deepinfra/bf16 | — | $16.6667 | $0.00 | — | — | 100.00% | |
| deepinfra/bf16 | — | $50.00 | $0.00 | — | — | 99.76% | |
| deepinfra/us | — | $7.50 | $0.00 | — | — | 100.00% | |
| deepinfra/us | — | $3.33 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 512 | $0.01 | $0.00 | — | — | 100.00% | |
| deepinfra/fp32 | 8K | $0.01 | $0.00 | — | — | 100.00% | |
| deepinfra/bf16 | 131K | $0.037 | $0.17 | — | — | 100.00% | |
| deepinfra/fp8 | 131K | $0.20 | $0.95 | — | — | 60.00% | |
| deepinfra/bf16 | 131K | $0.03 | $0.14 | — | — | 99.72% | |
| deepinfra/us | 512 | $0.005 | $0.00 | — | — | — | |
| deepinfra/us | 512 | $0.005 | $0.00 | — | — | — |
