---
title: "Thin authenticated proxy to Vertex AI generateContent"
method: POST
path: "/v4/fi-fast"
tags: ["v4", "Fi Fast"]
---

# Thin authenticated proxy to Vertex AI generateContent

`POST /v4/fi-fast`

## Request body

- FiFastRequest — Frontend-defined Vertex AI generateContent request.
  - `prompt` string, required — User message text
  - `system` string, nullable — System instruction
  - `tools` object[], nullable — Gemini tool/function declarations (pass-through)
  - `toolConfig` object, nullable — Tool calling config (e.g. mode: ANY)
  - `responseSchema` object, nullable — JSON Schema for structured output (alternative to tools)
  - `responseMimeType` string, 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
  - `thinkingBudget` integer, nullable — Thinking token budget (0 to disable, omit for model default)
  - `temperature` number — Sampling temperature
  - `maxOutputTokens` integer — Max output tokens

## Response `200`

Success

- SuccessResponseFiFastResponse
  - `success` true, required — Flag for it request was successful
  - `data` FiFastResponse, required — Raw Vertex AI response, passed through with minimal reshaping.
    - `content` object, required — candidates[0].content from Vertex AI response
    - `usage` object, nullable — usageMetadata from Vertex AI response
    - `model` string, required — Model used
    - `finishReason` string, nullable — Finish reason
  - `meta` ResponseMeta
    - `requestId` string — Unique request identifier for tracing
    - `timestamp` string, date-time — Response timestamp (UTC)
    - `durationMs` integer, nullable — Request processing time in milliseconds

## Other responses

- `401` — Auth Invalid Token
- `403` — Forbidden Insufficient Permissions
- `422` — Validation Failed
- `426` — Business Quota Exceeded
- `429` — Rate Limit Exceeded
- `500` — Internal Error
- `502` — External Service Error
- `503` — External Service Unavailable
- `504` — External Service Timeout

---

[API](https://skmtc.dev/definite/apis/defapi.md) · [All operations](https://skmtc.dev/definite/apis/defapi/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/definite/defapi/revisions/3943d8deb3be/schema)