Gemini 3 Flash Preview Chat API

google/gemini-3-flash-preview
1M tokens · 80 input / 480 output credits / 1M tokens

Gemini 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

Chat with Gemini 3 Flash Preview

Each model has its own conversation. Switching never sends another model's history, and switching back resumes where you left off. Requests are billed from actual token usage.

Ctrl / ⌘ + Enter to send0 / 32,000

Continue with

Gemini 3 Flash Preview Chat

Gemini 3 Flash Preview is Google's Gemini 3 model for fast chat, coding, and multimodal understanding. Its 1M-token context window can bring related files, documents, and conversation turns into one request, while adjustable thinking depth lets developers tune reasoning for the task. Vidgo offers Chat Completions and Gemini Native requests with complete JSON or SSE responses.

Why Choose Gemini 3 Flash Preview?

  • Responsive coding helpTurn requirements and source context into code drafts, reviews, and focused explanations.

  • Long-context synthesisCompare connected files and documents in a 1M-token context window.

  • Adjustable reasoningSet thinking depth for the complexity of the question and the response time you need.

  • Multimodal understandingAsk questions about text and media together through Gemini Native contents.

Parameters

ParameterRequirementDescription
modelChat Completions required

Use google/gemini-3-flash-preview.

messagesChat Completions required

A non-empty array of conversation messages.

contentsGemini Native required

A non-empty array of turns with role and parts; the model ID is in the URL.

contents[].parts[].inlineDataGemini Native optional

Inline media with mimeType and Base64 data alongside text parts.

generationConfigGemini Native optional

Set temperature, topP, topK, maxOutputTokens, or stopSequences for the response.

safetySettingsGemini Native optional

Safety settings for the request.

streamChat Completions optional

Set true for an SSE response.

Defaultfalsetrue

How to Use

  1. Describe the taskGive the goal, relevant context, and the form of answer you need.

  2. Choose a request formatSend messages through Chat Completions or contents through Gemini Native.

  3. Set generation controlsUse the form or JSON mode to set Temperature, Max Tokens, and Top P for a playground run.

  4. Review the responseRead the generated answer and token usage, then add the next turn as needed.

Pricing

Input and output tokens are billed separately. Rates apply per 1M tokens.

UsageRateDetails
Input$0.40 · 80 credits / 1M tokensRequest input tokens.
Output$2.40 · 480 credits / 1M tokensGenerated output tokens, including reasoning tokens recorded in usage.

Best Use Cases

  • Coding assistantsExplain code behavior and draft changes using source files and requirements.

  • Document analysisSummarize and compare long documents with a focused question.

  • Visual Q&ACombine an image and text instructions to extract relevant details.

Pro Tips

  • Place the goal and review criteria near the relevant source material.
  • In Gemini Native contents, put text instructions before inline media parts when practical.
  • Use the response usage fields to review input and output token counts.

Usage Notes

  • The context window is 1M tokens.
  • The on-page Playground offers a 256–8,192-token output control.
  • Use google/gemini-3-flash-preview in Chat Completions or in the Gemini Native model URL.

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.