API reference
generateContent
POST https://api.flyrouter.ai/v1beta/models/{model}:generateContent
POST https://api.flyrouter.ai/v1beta/models/{model}:streamGenerateContent?alt=sse
The Gemini native API. Requests and responses match the Google Gemini API, which suits projects already using the Google Gen AI SDK or Gemini CLI.
Example request
Terminal
curl "https://api.flyrouter.ai/v1beta/models/gemini-4-argon:generateContent" \
-H "x-goog-api-key: $FLYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"systemInstruction": {"parts": [{"text": "You are a concise assistant."}]},
"contents": [
{"role": "user", "parts": [{"text": "Introduce yourself in one sentence"}]}
],
"generationConfig": {"maxOutputTokens": 1024}
}'Streaming
Use streamGenerateContent with alt=sse. The response is SSE, and each event is a partial result:
Terminal
curl "https://api.flyrouter.ai/v1beta/models/gemini-4-argon:streamGenerateContent?alt=sse" \
-H "x-goog-api-key: $FLYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-N \
-d '{"contents": [{"role": "user", "parts": [{"text": "Write a short poem about autumn"}]}]}'Authentication
Use x-goog-api-key: sk-... or Authorization: Bearer sk-.... Avoid putting the key in URL parameters, since URLs tend to end up in logs.
Response
json
{
"candidates": [
{
"content": { "role": "model", "parts": [{ "text": "I am..." }] },
"finishReason": "STOP"
}
],
"usageMetadata": {
"promptTokenCount": 12,
"candidatesTokenCount": 30,
"totalTokenCount": 42
}
}:countTokens isn't supported yet. If you'd rather use the OpenAI SDK, Gemini models can also be called through Chat Completions.
FlyRouter