v4
Fi Fast
Thin authenticated proxy to Vertex AI generateContent
post/v4/fi-fast
Request body
promptstring required
User message text
systemstring nullable
System instruction
toolsobject[] nullable
Gemini tool/function declarations (pass-through)
toolConfigobject nullable
Tool calling config (e.g. mode: ANY)
responseSchemaobject nullable
JSON Schema for structured output (alternative to tools)
responseMimeTypestring nullable
e.g. application/json for JSON mode
model'gemini-3.1-pro-preview' | 'gemini-3.1-flash-lite-preview' | 'gemini-3-flash-preview' | 'gemini-2.5-flash-preview-05-20' | 'gemini-2.5-flash'
Vertex AI model
thinkingBudgetinteger nullable
Thinking token budget (0 to disable, omit for model default)
temperaturenumber
Sampling temperature
maxOutputTokensinteger
Max output tokens
Response
Success
successtrue required
Flag for it request was successful