SiliconFlow
Inference providerdocs.siliconflow.com ↗
Models on SiliconFlow · prices & measurements for models served by SiliconFlow’s APIUSD / MTOK · VERIFIED 4 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
| $0.04 | $0.18 | 131K | fp8 | 1.9s° | 57° tok/s | 4/5 | $0.03 elsewhere | |
| $0.05 | $0.45 | 131K | fp8 | 25.2s° | 10° tok/s | 3/5 | $0.03 elsewhere | |
| $0.07 | $0.28 | 262K | fp8 | 2.5s° | 49° tok/s | — | cheapest here | |
| $0.09 | $0.30 | 262K | fp8 | 2.4s° | 27° tok/s | — | $0.048 elsewhere | |
| $0.10 | $0.15 | 262K | fp8 | 2.3s° | 70° tok/s | — | cheapest here | |
| STStep 3.5 FlashStepFun | $0.10 | $0.30 | 262K | fp8 | 1.7s° | 81° tok/s | — | only provider |
| $0.12 | $0.40 | 262K | fp8 | 2s° | 125° tok/s | 5/5 | $0.042 elsewhere | |
| $0.13 | $0.28 | 1.05M | fp8 | 1.8s° | 56° tok/s | — | $0.056 elsewhere | |
| $0.13 | $0.40 | 262K | fp8 | 2.7s° | 82° tok/s | 5/5 | $0.08 elsewhere | |
| $0.14 | $0.28 | 1.05M | fp8 | 1.1s° | 66° tok/s | — | $0.04 elsewhere | |
| $0.14 | $0.86 | 131K | fp8 | 2.6s° | 50° tok/s | — | $0.13 elsewhere | |
| TEHunyuan A13B InstructTencent | $0.14 | $0.57 | 131K | fp8 | 2.9s° | 47° tok/s | — | only provider |
| $0.14 | $0.57 | 131K | fp8 | 5.8s° | 19° tok/s | — | $0.08 elsewhere | |
| $0.20 | $1.60 | 262K | fp8 | 1.9s° | 109° tok/s | — | $0.07 elsewhere | |
| $0.24 | $1.80 | 262K | fp8 | 2.3s° | 59° tok/s | 3/5 | $0.14 elsewhere | |
| $0.25 | $2.00 | 262K | fp8 | 3.6s° | 42° tok/s | 3/5 | $0.195 elsewhere | |
| $0.25 | $1.00 | 164K | fp8 | 2.5s° | 25° tok/s | — | $0.24 elsewhere | |
| $0.259 | $0.42 | 164K | fp8 | 2.5s° | 31° tok/s | 5/5 | $0.209 elsewhere | |
| $0.26 | $2.08 | 262K | fp8 | 1.9s° | 39° tok/s | 2/5 | cheapest here | |
| $0.27 | $0.41 | 164K | fp8 | 3s° | 45° tok/s | — | cheapest here | |
| $0.27 | $1.00 | 164K | fp8 | 1.7s° | 20° tok/s | — | cheapest here | |
| $0.27 | $1.00 | 164K | fp8 | 2s° | 23° tok/s | 5/5 | $0.25 elsewhere | |
| $0.29 | $1.00 | 262K | fp8 | 1.8s° | 71° tok/s | — | $0.20 elsewhere | |
| $0.29 | $1.00 | 262K | fp8 | 2.2s° | 46° tok/s | — | $0.13 elsewhere | |
| $0.30 | $3.20 | 262K | fp8 | 6.3s° | 39° tok/s | 2/5 | cheapest here | |
| $0.30 | $1.20 | 197K | fp8 | 1.7s° | 59° tok/s | — | $0.27 elsewhere | |
| $0.45 | $2.25 | 262K | int4 | 1.4s° | 79° tok/s | 5/5 | cheapest here | |
| NANex-N2-ProNEX AGI | $0.50 | $2.50 | 262K | — | 1.6s° | 161° tok/s | — | $0.25 elsewhere |
| $0.50 | $2.18 | 164K | fp8 | 1.9s° | 19° tok/s | — | cheapest here | |
| $0.77 | $3.40 | 262K | fp8 | 0.88s° | 101° tok/s | — | $0.58 elsewhere | |
| $0.859 | $3.80 | 262K | fp8 | 0.78s° | 77° tok/s | — | $0.67 elsewhere | |
| $0.95 | $2.55 | 205K | fp8 | 2.8s° | 80° tok/s | 2/5 | $0.60 elsewhere | |
| $1.19 | $3.74 | 1.05M | fp8 | 1.7s° | 87° tok/s | — | $0.50 elsewhere | |
| $1.19 | $3.74 | 205K | fp8 | 1.1s° | 54° tok/s | 2/5 | $0.91 elsewhere | |
| $1.32 | $3.96 | 1.05M | fp8 | 3.2s° | 86° tok/s | — | $0.66 elsewhere | |
| $1.50 | $3.13 | 1.05M | fp8 | 2.1s° | 54° tok/s | — | $0.522 elsewhere | |
| $2.00 | $6.00 | 1.05M | fp8 | 2.7s° | 49° tok/s | 5/5 | cheapest here |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) for SiliconFlow’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page