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.

ModelCreatorIn $/1MOut $/1MThroughputLatencyStatus
Nemotron 3 Nano (30B A3B)NVIDIA$0.06$0.24active
DeepSeek-V4-Flash-MaxDeepSeek$0.10$0.20active
Qwen3 30B A3BAlibaba Cloud / Qwen Team$0.10$0.30830.84active
Qwen3 32BAlibaba Cloud / Qwen Team$0.10$0.30271.19active
Qwen3 VL 4B InstructAlibaba Cloud / Qwen Team$0.10$0.60active
Qwen3 VL 4B ThinkingAlibaba Cloud / Qwen Team$0.10$1.00active
Gemma 4 31BGoogle$0.13$0.38active
MiMo-V2.5Xiaomi$0.40$2.00active
Seed 2.0 ProByteDance$0.50$3.00active
Kimi K2.7 CodeMoonshot AI$0.74$3.50active
Kimi K2.6Moonshot AI$0.75$3.50active
GLM-5.2Zhipu AI$0.95$3.00active
MiMo-V2.5-ProXiaomi$1.00$3.00active
DeepSeek-V4-Pro-MaxDeepSeek$1.74$3.48active
Via LLM Stats

14 listings

© 2026 NYSGPT2525 LLC