Gemini chat
Call the Gemini chat models available to your Essevin key through the OpenAI-compatible API.
Essevin exposes supported Gemini chat models through OpenAI Chat Completions. Use the same SDK and request shape as GPT, then select a Gemini model returned for the current key.
| Item | Value |
|---|---|
| Base URL | https://api.essevin.com/v1 |
| Endpoint | POST /v1/chat/completions |
| Authentication | Authorization: Bearer <Gemini-group key> |
| Model ID | Copy an exact ID from GET /v1/models |
The consumer catalog is intentionally smaller
A model shown in other Essevin products or public pricing is not automatically enabled for this key. Discover models with the selected Gemini-group key before configuring a client.
Discover a model first
curl https://api.essevin.com/v1/models \
-H "Authorization: Bearer $ESSEVIN_GEMINI_API_KEY"Choose a returned ID with the gemini- prefix. Common examples include gemini-3.5-flash and gemini-2.5-flash, but the response for the current key is authoritative.
Send a minimal request
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.essevin.com/v1",
api_key=os.environ["ESSEVIN_GEMINI_API_KEY"],
)
response = client.chat.completions.create(
model="gemini-3.5-flash",
messages=[{"role": "user", "content": "Reply with only ok"}],
)
print(response.choices[0].message.content)Stream responses with SSE
Add stream: true only when the application consumes SSE. Preserve the event stream end to end instead of buffering it into a single response.
curl https://api.essevin.com/v1/chat/completions \
-H "Authorization: Bearer $ESSEVIN_GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash",
"stream": true,
"messages": [{"role": "user", "content": "Reply with only ok"}]
}'Keep a Gemini-native request body
Existing Gemini integrations can keep the native contents field. The same Chat Completions endpoint detects the payload shape and forwards it in Gemini format.
curl https://api.essevin.com/v1/chat/completions \
-H "Authorization: Bearer $ESSEVIN_GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash",
"contents": [{"role": "user", "parts": [{"text": "Reply with only ok"}]}]
}'For Gemini image models, use the Image API instead of a chat request. Endpoints not documented on this consumer site are outside its supported model scope.