Gateway API
Chat Completions
Endpoint kompatibel OpenAI — POST /v1/chat/completions.
POST /v1/chat/completions menerima body persis seperti Chat Completions API milik OpenAI. Tidak ada field custom — cukup ganti model dan base URL.
Request
curl http://localhost:8080/v1/chat/completions \
-H "Authorization: Bearer sk_tr_..." \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o-mini",
"messages": [
{ "role": "system", "content": "Jawab singkat." },
{ "role": "user", "content": "Apa itu LLM gateway?" }
],
"stream": false
}'Respons yang kembali adalah format OpenAI standar, diperkaya dua header:
X-TeraRouter-Provider: openai
X-TeraRouter-Model: gpt-4o-miniStreaming
Set stream: true untuk menerima SSE — chunk-nya format OpenAI standar:
curl http://localhost:8080/v1/chat/completions \
-H "Authorization: Bearer sk_tr_..." \
-H "Content-Type: application/json" \
-d '{
"model": "glm/glm-4.6",
"messages": [{ "role": "user", "content": "Ceritakan lelucon" }],
"stream": true
}'Detail perilaku SSE (heartbeat, deadline, cross-dialect) ada di halaman Streaming.
Via SDK OpenAI
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: 'sk_tr_...',
baseURL: 'http://localhost:8080/v1',
})
const stream = await client.chat.completions.create({
model: 'openai/gpt-4o-mini',
messages: [{ role: 'user', content: 'Halo!' }],
stream: true,
})
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
}Memilih model
Nilai model tidak harus provider/model — kamu juga bisa memakai nama alias pool atau chain:<nama> supaya router yang memilih provider:
{ "model": "fast" }
{ "model": "chain:heavy-coding" }
{ "model": "anthropic/claude-sonnet-4(medium)" }Penjelasan lengkap: Model & routing.