zrouter

@zrouter

Multi-model AI inference provider with OpenAI-compatible access to frontier and open models. Built for developers, agents, coding tools, automation, and AI applications.

Joined 2026/10/499.9%RPM cap 1000

Service status

Model

24 hours agoNow

Availability

minimax-m3

—

qwen3.8-max

—

gpt-6.1-sol

—

grok-4.7

—

gpt-6-luna

—

gpt-6-sol

—

hy4-preview

—

qwen3.8-flash

—

deepseek-v4.1-flash

—

gemini-3.8-flash

—

AvailableDegradedUnavailableNo Data

Models (27)

Model	Input ($/M)	Output ($/M)	Actual input ($/M)	Cache ($/M)	Latency	Throughput	Uptime
minimax-m3	$0.015	$0.06	—	Hit rate— Read$0.003	—	—	99.7%
qwen3.8-max	$0.08	$0.24	—	Hit rate— Read$0.01 Write 5m$0.1	—	—	99.7%
gpt-6.1-sol	$0.07	$0.3	$0.04637	Hit rate35.5% Read$0.0035 Write 5m$0.0875	70.73s	5 tps	99.6%
grok-4.7	$0.07	$0.22	—	Hit rate— Read$0.0175	—	—	99.7%
gpt-6-luna	$0.005	$0.025	—	Hit rate— Read$0.0005 Write 5m$0.00625	—	—	99.7%
gpt-6-sol	$0.05	$0.2	—	Hit rate— Read$0.005 Write 5m$0.0625	—	—	99.7%
hy4-preview	$0.04	$0.12	—	Hit rate— Read$0.002014	—	—	99.7%
qwen3.8-flash	$0.0075	$0.0235	—	Hit rate— Read$0.0008 Write 5m$0.01	—	—	99.7%
deepseek-v4.1-flash	$0.0075	$0.03	—	Hit rate— Read$0.00015	—	—	99.7%
gemini-3.8-flash	$0.03	$0.15	—	Hit rate— Read$0.003 Write 5m$0.001667	—	—	99.7%

zrouter

Service status

Models (27)

Ratings (0)