GMI
GMICloud
Inference providerdocs.gmicloud.ai ↗
Models on GMICloud · prices & measurements for models served by GMICloud’s APIUSD / MTOK · VERIFIED 13 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
| $0.059 | $0.118 | 1.05M | fp8 | 2.5s° | 105° tok/s | 5/5 | $0.055 elsewhere | |
| $0.067 | $0.134 | 1.05M | fp4 | 2.5s° | 93° tok/s | — | $0.04 elsewhere | |
| $0.087 | $0.35 | 262K | fp8 | 1.5s° | 56° tok/s | — | cheapest here | |
| XIMiMo-V2.5XiaomiBEST PRICE | $0.119 | $0.238 | 1.05M | fp8 | 3s° | 51° tok/s | — | cheapest here |
| TEHy3TencentBEST PRICE | $0.126 | $0.522 | 262K | bf16 | 2.7s° | 50° tok/s | 2/5 | cheapest here |
| TEHy3 previewTencent | $0.18 | $0.60 | 262K | bf16 | 2.5s° | 58° tok/s | — | only provider |
| $0.209 | $0.31 | 164K | fp8 | 4.1s° | 33° tok/s | 5/5 | cheapest here | |
| $0.24 | $0.96 | 1.05M | fp8 | 2.5s° | 136° tok/s | 5/5 | $0.23 elsewhere | |
| $0.24 | $0.96 | 197K | fp8 | 1.4s° | 70° tok/s | 2/5 | cheapest here | |
| $0.29 | $1.14 | 164K | fp8 | 3.4s° | 45° tok/s | — | $0.24 elsewhere | |
| XIMiMo-V2.5-ProXiaomiBEST PRICE | $0.304 | $0.609 | 1.05M | bf16 | ✕ | ✕ | 4/5 | cheapest here |
| $0.528 | $1.58 | 1.05M | fp8 | 3.2s° | 58° tok/s | 4/5 | $0.522 elsewhere | |
| $0.60 | $3.60 | 262K | fp8 | ✕ | ✕ | — | $0.39 elsewhere | |
| $0.60 | $1.92 | 203K | fp8 | 1.7s° | 145° tok/s | 3/5 | cheapest here | |
| $0.91 | $2.86 | 203K | fp8 | 1.1s° | 87° tok/s | 3/5 | cheapest here | |
| $0.95 | $4.00 | 262K | fp8 | 2.3s° | 79° tok/s | — | $0.67 elsewhere | |
| $1.12 | $3.37 | 1.05M | fp8 | 3.2s° | 57° tok/s | 4/5 | $0.627 elsewhere | |
| $1.40 | $4.40 | 1.05M | fp8 | 1.5s° | 99° tok/s | — | $0.49 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) for GMICloud’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page