Completions
POST
/v1/completionsA legacy endpoint with a {model, prompt} body. The gateway turns prompt into a single user message and returns a chat.completion object — there is no choices[].text.
Request
curl https://api-dev.satulink.ai/v1/completions \
-H "Authorization: Bearer $SATULINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "deepseek-v-4.1-flash", "prompt": "Halo!" }'// client dibuat seperti di bagian SDK
const completion = await client.completions.create({
model: "deepseek-v-4.1-flash",
prompt: "Halo!",
});# client dibuat seperti di bagian SDK
completion = client.completions.create(
model="deepseek-v-4.1-flash",
prompt="Halo!",
)For new usage, use POST /v1/chat/completions.
Still haven't found the answer? Try it directly in Playground or view the list of active models.

