Gemini 3 Flash Preview
google/gemini-3-flash-previewGemini 3 Flash Preview is the preview release of the Flash tier in Google's Gemini 3 series, released in December 2025. Google described it at launch as its most powerful agentic and vibe-coding model to that point, built on Gemini 3 reasoning with multimodal understanding across text, image, video, audio and PDF input. It remains a preview endpoint with no announced shutdown date, and Google recommends Gemini 3.6 Flash as its replacement.
- Input price
- $0.50USD / 1M tokens
- Output price
- $3.00USD / 1M tokens
- Context window
- 1M
- Max output
- 65.5K
Try the model
Playground
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Model card
Specifications
Pricing
- Input
- $0.50 / 1M tokens
- Output
- $3 / 1M tokens
- Cache read
- $0.05 / 1M tokens
Context & modalities
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Input
- Text, image
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Supported
- Reasoning
- Supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Supported
Access
- Provider
- Model ID
- google/gemini-3-flash-preview
- Execution
- sync
- Base URL
- https://api.sandbase.ai
- API
- Chat Completions API
- Endpoint
- /v1/chat/completions
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v4.3
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "google/gemini-3-flash-preview",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Gemini 3 Flash PreviewThis model Google | 1M | $0.50 | $3.00 | Dec 17, 2025 |
Google | 1M | $4.00 | $20.00 | Oct 13, 2026 |
Google | 64K | $1.50 | $7.50 | Oct 8, 2026 |
Google | 1M | $1.50 | $7.50 | Sep 2, 2026 |
Google | 1M | $1.50 | $7.50 | Aug 13, 2026 |
Google | 1M | $0.30 | $2.50 | Jul 21, 2026 |
Questions
FAQ
How do I call Google Gemini 3 Flash Preview through SandBase?
Create a SandBase API key, then send requests with the model ID "google/gemini-3-flash-preview" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.
How much does Google Gemini 3 Flash Preview cost?
$0.50 per 1M input tokens and $3 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.
What is the context window of Google Gemini 3 Flash Preview?
1M tokens of context, with up to 65.5K output tokens per response.
How does Google Gemini 3 Flash Preview score on benchmarks?
Google Gemini 3 Flash Preview scores 26.3 on the Artificial Analysis Intelligence Index (v4.3), ranking #50 of 87 models on SandBase. Source: Artificial Analysis, measured as Gemini 3 Flash Preview (Reasoning).
Which features does Google Gemini 3 Flash Preview support?
Google Gemini 3 Flash Preview supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.
Do I need a separate Google account?
No. One SandBase API key and balance gives you access to Google Gemini 3 Flash Preview and the other models in the catalog; you do not need to sign up with Google separately.