Models
14
served
Labs
8
covered
Cheapest in
$0.06
input $/1M
Cheapest out
$0.20
output $/1M
Median t/s
55
throughput
Median lat
1.01
seconds
Measured
2 / 14
with latency
Status
All active
active listings
Catalog
Every tracked model this host serves, on its own terms — cheapest input first.
| Model | Creator | In $/1M | Out $/1M | Throughput | Latency | Status |
|---|---|---|---|---|---|---|
| Nemotron 3 Nano (30B A3B) | NVIDIA | $0.06 | $0.24 | — | — | active |
| DeepSeek-V4-Flash-Max | DeepSeek | $0.10 | $0.20 | — | — | active |
| Qwen3 30B A3B | Alibaba Cloud / Qwen Team | $0.10 | $0.30 | 83 | 0.84 | active |
| Qwen3 32B | Alibaba Cloud / Qwen Team | $0.10 | $0.30 | 27 | 1.19 | active |
| Qwen3 VL 4B Instruct | Alibaba Cloud / Qwen Team | $0.10 | $0.60 | — | — | active |
| Qwen3 VL 4B Thinking | Alibaba Cloud / Qwen Team | $0.10 | $1.00 | — | — | active |
| Gemma 4 31B | $0.13 | $0.38 | — | — | active | |
| MiMo-V2.5 | Xiaomi | $0.40 | $2.00 | — | — | active |
| Seed 2.0 Pro | ByteDance | $0.50 | $3.00 | — | — | active |
| Kimi K2.7 Code | Moonshot AI | $0.74 | $3.50 | — | — | active |
| Kimi K2.6 | Moonshot AI | $0.75 | $3.50 | — | — | active |
| GLM-5.2 | Zhipu AI | $0.95 | $3.00 | — | — | active |
| MiMo-V2.5-Pro | Xiaomi | $1.00 | $3.00 | — | — | active |
| DeepSeek-V4-Pro-Max | DeepSeek | $1.74 | $3.48 | — | — | active |
Via LLM Stats
14 listings