Status

Satu endpoint untuk seluruh model AI.

Pakai API OpenAI-compatible untuk layanan Multi-Model dan Grok. Satu base URL, autentikasi Bearer sk-user.

Lihat harga Baca dokumentasi all ready

base url

https://api.ngawi-proxy.cloud/v1

multi-model

READY

grok

READY

protokol

OpenAI v1

Multi-Model

READY

GLM, DeepSeek, GPT, Claude via /v1/chat/completions

4model tersedia

glm-5.2
deepseek-v4-flash
deepseek-v4-pro
deepseek-v4-mod

curl https://api.ngawi-proxy.cloud/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-5.2","stream":true,"messages":[{"role":"user","content":"hi"}]}'

Grok

READY

Grok chat + Imagine image via /v1 · model selection = GET /v1/models

7model tersedia

grok-4.5
grok-4.5-low
grok-4.5-medium
grok-4.5-high
grok-imagine-image
grok-imagine-image-edit
grok-imagine-image-quality

curl https://api.ngawi-proxy.cloud/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-4.5","stream":true,"messages":[{"role":"user","content":"hi"}]}'

Catatan pakai

Plan Grok: model default grok-4.5 (alias low/medium/high = effort)
Model selection: GET /v1/models (sumber kebenaran)
Plan Multi: deepseek-v4-flash / glm-5.2 / gpt-5.6 / claude-sonnet-5
Gunakan stream=true untuk chat / agent panjang
Set client timeout 300–600 detik
Image: POST /v1/images/generations (grok-imagine-image)
Cek sisa kuota di /usage atau GET /api/me