Gemini 3 Flash Preview Chat API
google/gemini-3-flash-previewGemini 3 Flash Preview Chat turns text and multimodal context into answers, code, and analysis with a 1M-token context window and adjustable reasoning depth. Supply the relevant material and instructions to keep long conversations focused on the requested result.
Gemini 3 Flash Preview
Google · chat-completions
Quick start
Send a POST request to /v1/chat/completions with google/gemini-3-flash-preview. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- google/gemini-3-flash-preview
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | google/gemini-3-flash-preview |
| messages | Required | A non-empty array of conversation messages. |
| max_tokens | Optional | Limits output tokens for this response. |
| temperature | Optional | Sampling temperature; the playground allows 0–2. |
| top_p | Optional | Nucleus sampling probability; the playground allows 0–1. |
| stream | Optional | Returns an SSE event stream when true. |
Response and usage
Successful responses include generated content and usage. Billing settles from actual input, output, and cache tokens.
Streaming
Set stream: true to read SSE. Finalize usage accounting from the terminal usage event.
curl --request POST \
--url https://api.vidgo.ai/v1/chat/completions \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "google/gemini-3-flash-preview",
"messages": [
{
"role": "user",
"content": "Explain why deterministic retries matter in distributed systems."
}
],
"max_tokens": 1024,
"temperature": 1,
"top_p": 1,
"stream": false
}'Keep API keys on the server. Never expose them in browser code or public repositories.
Continue with
Related Models
Gemini 3 Flash Preview Chat API frequently asked questions
What is the Gemini 3 Flash Preview Chat API?
Gemini 3 Flash Preview is Google's Gemini 3 model for chat, coding, and multimodal understanding. It turns text and media context into answers, analysis, and code with a 1M-token context window and adjustable reasoning depth. Use Chat Completions or Gemini Native to call the model, or try it in the playground above.
How does Gemini 3 Flash Preview handle long documents?
Its 1M-token context window lets you send related documents and a clear question in one request. Ask for a summary, comparison, or findings tied to passages in the supplied material.
How can I send images to Gemini 3 Flash Preview?
In Gemini Native contents, add a text part and an inlineData part with mimeType and Base64 data. State the image details you want examined in the text part.
How do I stream Gemini 3 Flash Preview responses?
Set stream to true in Chat Completions, or call streamGenerateContent?alt=sse with Gemini Native contents. Read the SSE events in order and inspect usageMetadata for token counts.
What does Gemini 3 Flash Preview cost on Vidgo AI?
Input costs 80 credits ($0.40) and output costs 480 credits ($2.40) per 1M tokens. Check response usage and the Pricing table above for the rate applied to each token direction.