Gemini 3.8 Flash
vichar-gemini-3.8-flash
Gemini 3.8 Flash, a fast multimodal model for latency-sensitive workloads.
- Context window
- 1.0M
- Max output
- 66k
- Input
- $0.75 /M tokens
- Output
- $3.75 /M tokens
Supported parameters
- max_tokens
- response_format
- reasoning_effort
- tools
- tool_choice
- reasoning
curl https://api.vichar.io/v1/chat/completions \
-H "Authorization: Bearer $VICHAR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "vichar-gemini-3.8-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'