Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| CSM 1B | deepinfra/us | 4K | $7.00 | $0.00 | — | — | 100.00% |
| deepinfra/bf16 | 66K | $0.12 | $0.00 | — | — | 100.00% | |
| deepinfra/bf16 | 66K | $0.02 | $0.00 | — | — | 100.00% | |
| deepinfra/fp4 | 164K | $0.32 | $0.89 | — | — | 87.64% | |
| deepinfra/fp4 | 164K | $0.25 | $0.95 | $0.13 | — | 100.00% | |
| deepinfra/fp4 | 164K | $0.26 | $0.38 | $0.13 | — | 96.32% | |
| deepinfra/fp8 | 1.0M | $0.09 | $0.18 | $0.02 | — | 99.66% | |
| deepinfra/fp8 | 1.0M | $0.06 | $0.18 | $0.02 | — | 100.00% | |
| deepinfra/fp8 | 1.0M | $0.22 | $0.65 | $0.00686 | — | 100.00% | |
| deepinfra/fp8 | 1.0M | $1.30 | $2.60 | $0.10 | — | 100.00% | |
| deepinfra/fp8 | 1.0M | $1.30 | $2.60 | $0.10 | — | 99.64% | |
| deepinfra/fp8 | 1.0M | $0.14 | $0.42 | $0.0042 | — | 100.00% | |
| deepinfra | 131K | $0.04 | $0.00 | — | — | 100.00% | |
| deepinfra | 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 | — | 99.86% | |
| deepinfra/fp4 | 203K | $0.40 | $1.75 | $0.08 | — | 59.58% | |
| deepinfra/fp4 | 1.0M | $0.56 | $1.80 | $0.11 | — | 99.43% | |
| deepinfra/fp4 | 1.0M | $0.56 | $2.50 | $0.13 | — | 98.89% | |
| deepinfra/fp4 | 1.0M | $0.08 | $0.25 | $0.02 | — | 99.11% | |
| 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 | — | — | 99.93% | |
| deepinfra/fp8 | 131K | $0.08 | $0.16 | — | — | 99.30% | |
| 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/turbo | 262K | $0.09 | $0.34 | $0.05 | — | 100.00% | |
| deepinfra/bf16 | 131K | $0.06 | $0.25 | $0.02 | — | 100.00% | |
| deepinfra/fp8 | 131K | $1.00 | $1.00 | — | — | 99.84% | |
| deepinfra/fp8 | 131K | $0.70 | $0.70 | — | — | 100.00% | |
| deepinfra/fp8 | 1.0M | $0.83 | $2.50 | $0.04 | — | 100.00% | |
| deepinfra/fp8 | 524K | $0.95 | $4.05 | $0.16 | — | 98.38% | |
| deepinfra/fp8 | 524K | $0.45 | $1.20 | $0.10 | — | 100.00% | |
| deepinfra/fp4 | 262K | $0.75 | $3.50 | $0.15 | — | 97.38% | |
| deepinfra/mxfp4 | 1.0M | $2.85 | $14.25 | $0.29 | — | 99.93% | |
| Kokoro 82M | deepinfra/us | 4K | $0.62 | $0.00 | — | — | 100.00% |
| deepinfra/bf16 | 131K | $0.06 | $0.18 | $0.01 | — | 98.95% | |
| deepinfra/fp16 | 131K | $0.06 | $0.18 | $0.01 | — | 99.17% | |
| deepinfra/fp4 | 262K | $0.30 | $0.90 | $0.06 | — | 97.41% | |
| Llama 3 8B Lunaris | deepinfra/turbo | 8K | $0.04 | $0.05 | — | — | 100.00% |
| deepinfra/turbo | 131K | $0.40 | $0.40 | — | — | 96.29% | |
| deepinfra/fp8 | 131K | $0.02 | $0.04 | — | — | 100.00% | |
| Llama 3.1 Euryale 70B v2.2 | deepinfra/fp8 | 131K | $0.85 | $0.85 | — | — | 100.00% |
| deepinfra/turbo | 131K | $0.10 | $0.32 | — | — | 96.81% | |
| deepinfra/fp8 | 328K | $0.10 | $0.30 | — | — | 99.59% | |
| deepinfra/bf16 | 164K | $0.18 | $0.18 | — | — | 99.93% | |
| deepinfra/fp8 | 1.0M | $0.13 | $0.27 | $0.00266 | — | 88.53% | |
| deepinfra/fp8 | 1.0M | $0.43 | $0.87 | $0.0036 | — | 100.00% | |
| deepinfra/fp8 | 524K | $0.28 | $1.10 | $0.06 | — | 99.91% | |
| deepinfra/fp8 | 131K | $0.03 | $0.03 | — | — | 100.00% | |
| deepinfra/fp8 | 33K | $0.05 | $0.08 | — | — | 100.00% | |
| deepinfra/fp8 | 128K | $0.08 | $0.20 | — | — | 99.93% | |
| Multilingual-E5-Large | deepinfra/fp32 | 512 | $0.01 | $0.00 | — | — | 100.00% |
| deepinfra/bf16 | 131K | $0.30 | $1.20 | $0.04 | — | 100.00% | |
| MythoMax 13B | deepinfra/fp16 | 4K | $0.40 | $0.40 | — | — | 100.00% |
| deepinfra/bf16 | 262K | $0.08 | $0.40 | — | — | 100.00% | |
| deepinfra/fp4 | 262K | $0.50 | $2.20 | $0.10 | — | 100.00% | |
| deepinfra/us | — | $3.33 | $0.00 | — | — | 99.71% | |
| deepinfra/bf16 | 131K | $0.20 | $0.20 | — | — | 100.00% | |
| deepinfra/bf16 | 262K | $0.06 | $0.16 | $0.03 | — | 99.33% | |
| Orpheus 3B | deepinfra/us | 4K | $7.00 | $0.00 | — | — | 83.33% |
| deepinfra/bf16 | 16K | $0.07 | $0.14 | — | — | 100.00% | |
| deepinfra/fp8 | 33K | $0.36 | $0.40 | — | — | 99.72% | |
| deepinfra/fp8 | 41K | $0.12 | $0.24 | — | — | 98.21% | |
| deepinfra/fp8 | 262K | $0.09 | $0.55 | — | — | 99.31% | |
| deepinfra/fp8 | 41K | $0.12 | $0.50 | — | — | 100.00% | |
| deepinfra/fp8 | 41K | $0.08 | $0.28 | — | — | 99.24% | |
| deepinfra/us | — | $3.33 | $0.00 | — | — | 100.00% | |
| deepinfra/us | — | $7.50 | $0.00 | — | — | 99.15% | |
| deepinfra/turbo | 262K | $0.30 | $1.00 | $0.10 | — | 93.17% | |
| deepinfra/us | 33K | $0.02 | $0.00 | — | — | 100.00% | |
| deepinfra/us | 33K | $0.01 | $0.00 | — | — | 100.00% | |
| deepinfra/fp8 | 262K | $0.09 | $1.10 | — | — | 96.94% | |
| deepinfra/fp8 | 262K | $0.20 | $0.88 | $0.11 | — | 99.79% | |
| deepinfra/fp8 | 262K | $0.15 | $0.60 | — | — | 99.10% | |
| deepinfra/fp8 | 262K | $0.45 | $3.00 | $0.22 | — | 100.00% | |
| deepinfra/fp8 | 262K | $0.26 | $2.60 | — | — | 100.00% | |
| deepinfra/fp8 | 262K | $0.14 | $1.00 | $0.05 | — | 99.60% | |
| deepinfra/bf16 | 262K | $0.10 | $0.15 | — | — | 99.70% | |
| deepinfra/fp8 | 262K | $0.32 | $3.20 | — | — | 99.92% | |
| deepinfra/fp8 | 262K | $0.10 | $0.95 | $0.10 | — | 77.17% | |
| deepinfra/bf16 | 262K | $0.15 | $1.88 | $0.04 | — | 75.69% | |
| deepinfra/fp4 | 164K | $0.50 | $2.15 | $0.35 | — | 99.93% | |
| deepinfra/fp8 | 1.0M | $1.00 | $2.70 | $0.05 | — | 88.74% | |
| deepinfra/bf16 | — | $16.67 | $0.00 | — | — | 100.00% | |
| deepinfra/bf16 | — | $50.00 | $0.00 | — | — | 98.68% | |
| deepinfra/us | — | $7.50 | $0.00 | — | — | 100.00% | |
| deepinfra/us | — | $3.33 | $0.00 | — | — | 100.00% | |
| all-MiniLM-L12-v2 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% |
| all-MiniLM-L6-v2 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 99.93% |
| all-mpnet-base-v2 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 99.28% |
| bge-base-en-v1.5 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% |
| bge-large-en-v1.5 | deepinfra/us | 512 | $0.01 | $0.00 | — | — | 100.00% |
| bge-m3 | deepinfra/fp32 | 8K | $0.01 | $0.00 | — | — | 100.00% |
| deepinfra/bf16 | 131K | $0.04 | $0.17 | — | — | 99.93% | |
| deepinfra/turbo | 131K | $0.15 | $0.60 | — | — | 100.00% | |
| deepinfra/bf16 | 131K | $0.03 | $0.14 | — | — | 99.70% | |
| multi-qa-mpnet-base-dot-v1 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% |
| paraphrase-MiniLM-L6-v2 | deepinfra/us | 512 | $0.005 | $0.00 | — | — | 100.00% |
