34 models
registration closed
sakuragarden.web.id
sakura garden gateway
private proxy routing 34 open models through an encrypted edge.
gateway status
host
sakuragarden.web.id
protocol
openai v1 sse
catalog
34 models
quotas
unlimited
allowed models
all models route without suffix. requests are redirected upstream automatically.
deepseek
deepseek-v3.1
daily limit:
unlimited
deepseek
deepseek-v3.2
daily limit:
unlimited
deepseek
deepseek-v4-flash
daily limit:
unlimited
deepseek
deepseek-v4-pro
daily limit:
unlimited
deepseek
deepseek-v4.1-flash
daily limit:
unlimited
glm
glm-5.1
daily limit:
unlimited
glm
glm-5.2
daily limit:
unlimited
glm
glm-5.3
daily limit:
unlimited
glm
glm-5.3-flash
daily limit:
unlimited
hy
hy3
daily limit:
unlimited
kimi
kimi-k2.6
daily limit:
unlimited
kimi
kimi-k2.7-code
daily limit:
unlimited
kimi
kimi-k2.8
daily limit:
unlimited
kimi
kimi-k3
daily limit:
unlimited
llama
llama-3.3-70b-instruct-turbo
daily limit:
unlimited
magistral
magistral-small
daily limit:
unlimited
minimax
minimax-m2
daily limit:
unlimited
minimax
minimax-m2.1
daily limit:
unlimited
minimax
minimax-m2.5
daily limit:
unlimited
mistral
ministral-3-14b-instruct
daily limit:
unlimited
mistral
ministral-3-3b-instruct
daily limit:
unlimited
mistral
ministral-3-8b-instruct
daily limit:
unlimited
mistral
ministral-3b-2512
daily limit:
unlimited
mistral
mistral-large-3
daily limit:
unlimited
muse
muse-spark-1.2-contributor
daily limit:
unlimited
muse
muse-spark-1.3-contributor
daily limit:
unlimited
mythomax
mythomax-l2-13b
daily limit:
unlimited
qwen
qwen-3.8-27b
daily limit:
unlimited
qwen
qwen3-235b-a22b
daily limit:
unlimited
qwen
qwen3-30b-a3b
daily limit:
unlimited
qwen
qwen3-32b
daily limit:
unlimited
qwen
qwen3-next-80b-a3b-instruct
daily limit:
unlimited
qwen
qwen3-vl-235b-a22b-instruct
daily limit:
unlimited
qwen
qwen3.8-flash
daily limit:
unlimited
client integration
standard configuration values for third-party clients and developer libraries.
janitor ai
in api settings, select proxy tab and set:
https://sakuragarden.web.id/v1/chat/completions
model: qwen3.8-flash
sillytavern
in api connection, choose custom openai-compatible and set:
https://sakuragarden.web.id/v1
model: qwen3.8-flash
cursor ide
in cursor settings, configure custom api provider:
https://sakuragarden.web.id/v1
model: qwen3.8-flash