DeepInfra
Models on DeepInfra · prices & measurements for models served by DeepInfra’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
| $0.019 | $0.03 | 131K | fp8 | 0.76s° | 33° tok/s | — | $0.018 elsewhere | |
| $0.02 | $0.04 | 131K | fp8 | ✕ | ✕ | 3/5 | cheapest here | |
| $0.03 | $0.14 | 131K | bf16 | 0.28s° | 100° tok/s | 2/5 | $0.018 elsewhere | |
| $0.037 | $0.17 | 131K | bf16 | 0.46s° | 48° tok/s | 4/5 | $0.03 elsewhere | |
| $0.04 | $0.05 | 8K | fp8 | 0.28s° | 99° tok/s | — | cheapest here | |
| $0.05 | $0.20 | 262K | fp4 | 1.2s° | 114° tok/s | — | cheapest here | |
| $0.05 | $0.10 | 131K | bf16 | ✕ | ✕ | — | only provider | |
| $0.05 | $0.15 | 131K | bf16 | 0.93s° | 39° tok/s | — | cheapest here | |
| $0.05 | $0.08 | 33K | fp8 | 0.88s° | 60° tok/s | — | only provider | |
| $0.06 | $0.18 | 131K | fp16 | ✕ | ✕ | — | $0.021 elsewhere | |
| $0.06 | $0.25 | 131K | bf16 | 1.6s° | 79° tok/s | — | cheapest here | |
| $0.06 | $0.18 | 262K | fp4 | 0.43s° | 189° tok/s | — | $0.042 elsewhere | |
| $0.06 | $0.16 | 262K | bf16 | 0.32s° | 455° tok/s | — | $0.039 elsewhere | |
| $0.06 | $0.18 | 1.05M | fp8 | 0.91s° | 47° tok/s | — | $0.01 elsewhere | |
| $0.06 | $0.18 | 131K | bf16 | ✕ | ✕ | — | $0.021 elsewhere | |
| $0.07 | $0.34 | 262K | fp8 | 0.68s° | 30° tok/s | 5/5 | $0.042 elsewhere | |
| $0.07 | $0.14 | 16K | bf16 | 1.1s° | 75° tok/s | — | only provider | |
| $0.075 | $0.25 | 1.05M | fp4 | ✕ | ✕ | — | $0.032 elsewhere | |
| $0.075 | $0.20 | 128K | fp8 | ✕ | ✕ | — | cheapest here | |
| $0.08 | $0.28 | 41K | fp8 | 1.5s° | 27° tok/s | — | cheapest here | |
| $0.08 | $0.16 | 131K | fp8 | ✕ | ✕ | 3/5 | cheapest here | |
| $0.085 | $0.40 | 262K | bf16 | ✕ | ✕ | — | $0.08 elsewhere | |
| $0.09 | $0.18 | 1.05M | fp8 | ✕ | ✕ | 5/5 | $0.017 elsewhere | |
| $0.09 | $0.34 | 262K | fp4 | ✕ | ✕ | 5/5 | cheapest here | |
| $0.09 | $1.10 | 262K | fp8 | 0.5s° | 31° tok/s | — | cheapest here | |
| $0.09 | $0.55 | 262K | fp8 | 0.5s° | 30° tok/s | 5/5 | $0.087 elsewhere | |
| $0.10 | $0.95 | 262K | fp8 | 0.62s° | 43° tok/s | 2/5 | $0.05 elsewhere | |
| $0.10 | $0.15 | 262K | bf16 | 0.77s° | 48° tok/s | — | $0.08 elsewhere | |
| $0.10 | $0.30 | 328K | fp8 | 0.43s° | 62° tok/s | — | cheapest here | |
| $0.10 | $0.32 | 131K | fp8 | 1.7s° | 39° tok/s | 5/5 | cheapest here | |
| $0.12 | $0.50 | 41K | fp8 | 0.42s° | 52° tok/s | — | cheapest here | |
| $0.12 | $0.24 | 41K | fp8 | 0.86s° | 57° tok/s | — | $0.10 elsewhere | |
| $0.13 | $0.53 | 262K | fp4 | 0.73s° | 178° tok/s | 2/5 | cheapest here | |
| $0.14 | $0.28 | 1.05M | fp8 | ✕ | ✕ | — | $0.10 elsewhere | |
| $0.14 | $0.42 | 1.05M | fp8 | 0.36s° | 145° tok/s | — | $0.018 elsewhere | |
| $0.14 | $1.00 | 262K | fp8 | 1.8s° | 104° tok/s | 3/5 | $0.08 elsewhere | |
| $0.15 | $1.88 | 262K | bf16 | 1.3s° | 35° tok/s | — | $0.024 elsewhere | |
| $0.15 | $0.60 | 262K | fp8 | 0.51s° | 36° tok/s | — | $0.13 elsewhere | |
| $0.18 | $0.18 | 164K | bf16 | ✕ | ✕ | — | only provider | |
| $0.20 | $0.20 | 131K | bf16 | ✕ | ✕ | — | only provider | |
| $0.20 | $0.88 | 262K | fp8 | ✕ | ✕ | — | cheapest here | |
| $0.216 | $0.647 | 1.05M | fp8 | 0.51s° | 190° tok/s | — | cheapest here | |
| $0.25 | $0.95 | 164K | fp4 | ✕ | ✕ | 5/5 | cheapest here | |
| $0.26 | $2.60 | 262K | fp8 | ✕ | ✕ | 3/5 | $0.195 elsewhere | |
| $0.26 | $0.38 | 164K | fp4 | 1.1s° | 13° tok/s | 5/5 | $0.209 elsewhere | |
| $0.28 | $1.10 | 524K | fp8 | ✕ | ✕ | 5/5 | $0.23 elsewhere | |
| $0.30 | $1.20 | 131K | bf16 | 0.94s° | 85° tok/s | — | cheapest here | |
| $0.30 | $1.00 | 262K | fp4 | ✕ | ✕ | — | $0.22 elsewhere | |
| $0.32 | $3.20 | 262K | fp8 | ✕ | ✕ | 2/5 | $0.30 elsewhere | |
| $0.32 | $0.89 | 164K | fp4 | 0.73s° | 18° tok/s | — | $0.257 elsewhere | |
| $0.36 | $0.40 | 33K | fp8 | 2.2s° | 30° tok/s | — | cheapest here | |
| $0.40 | $1.75 | 203K | fp4 | ✕ | ✕ | 2/5 | cheapest here | |
| $0.40 | $0.40 | 131K | fp8 | 1.5s° | 41° tok/s | — | cheapest here | |
| $0.40 | $0.40 | 4K | fp16 | 0.28s° | 53° tok/s | — | $0.08 elsewhere | |
| $0.43 | $0.87 | 1.05M | fp8 | ✕ | ✕ | — | cheapest here | |
| $0.45 | $1.20 | 524K | fp8 | ✕ | ✕ | — | only provider | |
| $0.45 | $3.00 | 262K | fp8 | ✕ | ✕ | 3/5 | $0.39 elsewhere | |
| $0.50 | $2.20 | 262K | fp4 | 1s° | 267° tok/s | — | cheapest here | |
| $0.50 | $2.00 | 203K | fp4 | ✕ | ✕ | 3/5 | $0.43 elsewhere | |
| $0.50 | $2.15 | 164K | fp4 | 0.56s° | 41° tok/s | — | cheapest here | |
| $0.563 | $2.50 | 1.05M | fp4 | 0.92s° | 147° tok/s | — | $0.039 elsewhere | |
| $0.563 | $1.80 | 1.05M | fp4 | 0.87s° | 92° tok/s | — | $0.03 elsewhere | |
| $0.70 | $0.70 | 131K | fp8 | ✕ | ✕ | — | only provider | |
| $0.75 | $3.50 | 262K | fp4 | 1.4s° | 34° tok/s | — | $0.465 elsewhere | |
| $0.834 | $2.50 | 1.05M | fp8 | — | — | — | cheapest here | |
| $0.85 | $0.85 | 131K | fp8 | 1.7s° | 48° tok/s | — | cheapest here | |
| $0.95 | $4.05 | 524K | fp8 | 0.38s° | 261° tok/s | — | cheapest here | |
| $1.00 | $1.00 | 131K | fp8 | ✕ | ✕ | — | only provider | |
| $1.30 | $2.60 | 1.05M | fp8 | 0.94s° | 54° tok/s | — | $0.158 elsewhere | |
| $1.30 | $2.60 | 1.05M | fp8 | ✕ | ✕ | — | $0.30 elsewhere | |
| $2.00 | $6.00 | 262K | fp4 | 1.3s° | 87° tok/s | 4/5 | cheapest here | |
| $2.85 | $14.25 | 1.05M | mxfp4 | 1.3s° | 74° tok/s | 4/5 | $0.68 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for DeepInfra’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page