Qwen BF16 Streaming
128K
112tok/s
3,240tok/s
0.24s · p50
$0.18/ 1M tok
$0.38/ 1M tok
THE OPEN INFERENCE MARKETPLACE
The model you want.
The provider you choose.
Compare inference by performance, price, and trust.
Preview network
15 example models · 5 modalities
Live inference is coming next.
/
Explore inference 8 deployments
Demo catalog. Providers, prices, benchmark results, and trust scores are illustrative.
Frankfurt, DE
DeepSeek BF16 Streaming
128K
64tok/s
2,180tok/s
0.48s · p50
$0.42/ 1M tok
$0.65/ 1M tok
Meta BF16 Streaming
128K
87tok/s
2,860tok/s
0.31s · p50
$0.35/ 1M tok
$0.58/ 1M tok
Qwen AWQ INT4 Streaming
128K
156tok/s
4,100tok/s
0.19s · p50
$0.14/ 1M tok
$0.29/ 1M tok
Qwen BF16 Streaming
32K
214tok/s
6,280tok/s
0.12s · p50
$0.04/ 1M tok
$0.08/ 1M tok
Google FP8 Streaming
128K
72tok/s
2,300tok/s
0.39s · p50
$0.12/ 1M tok
$0.22/ 1M tok
Meta GPTQ INT4 Streaming
32K
102tok/s
1,700tok/s
0.44s · p50
$0.03/ 1M tok
$0.06/ 1M tok
Qwen BF16 Streaming
128K
94tok/s
3,100tok/s
0.28s · p50
$0.16/ 1M tok
$0.32/ 1M tok
All 8 matching sample deployments shownBring your model to the network