Gemini 3 Flash (Preview) API status on Google Gemini

Check provider

Available from Google Gemini

Catalog metadata matched Reasoning models.dev metadata

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Check providerOpenAI compatibleReasoningTool callingJSON modePDF inputText

Check Provider Compare Save API Key

API Details

Copy-ready connection details

Use these values in your client or SDK.

Base URL

https://generativelanguage.googleapis.com/v1beta

Model ID

gemini-3-flash-preview

API format Google Gemini native generateContent + OpenAI Chat Completions

Technical Details

Gemini 3 Flash (Preview) specifications

Provider and model catalog

Context window 1.0M

Max output 65K

Status Check provider

Family gemini-flash

Knowledge cutoff 2025-01

Released Dec 17, 2025

Last updated May 23, 2026

Free listing since Dec 17, 2025

Input text, image, video, audio, pdf

Output text

Capabilities reasoning, tool calling, structured output, file attachments, temperature control

External benchmark references

Benchmark	Score	Metric	Date
SWE-Bench Pro	34.63	resolve rate	Not listed
SWE-Atlas Codebase QnA	8.2	score	Not listed
SWE-Atlas Refactoring	10	score	Not listed
SWE-Atlas Test Writing	30.3	score	Not listed

AI Recommendation

Should you use Gemini 3 Flash (Preview)?

Gemini 3 Flash (Preview) is listed for chat workloads and supports a 1.0M context window.

Check Google Gemini's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.

Best for

Chat

Strengths & Weaknesses

Strengths

Long context window
Reasoning mode listed
Tool calling support
Structured JSON output

Watch outs

Current endpoint availability needs provider confirmation
Free-tier rate limits apply
Vision support is not listed

Pricing

Gemini 3 Flash (Preview) pricing per 1M tokens

Check provider

Input $0.5 per 1M tokens

Output $3 per 1M tokens

Free access Check provider Google Gemini

Rate limit Preview limits provider policy

Availability

Gemini 3 Flash (Preview) availability by provider

Current provider only

We only found this Gemini 3 Flash (Preview) listing on Google Gemini in the current catalog. Use the related models section for nearby alternatives.

Provider	Model listing	Access	Context	API	Limits
Google Gemini	Gemini 3 Flash (Preview)	Check provider	1.0M	Native	Preview limits

View Google Gemini setup guide →

Compare

Gemini 3 Flash (Preview) alternatives to consider

Open comparison

Model	Provider	Context	Access
Gemini 3.6 Flash	Google Gemini	1.0M	Free tier
Gemini 3.5 Flash	Google Gemini	1.0M	Free tier
Gemini 3.5 Flash-Lite	Google Gemini	1.0M	Free tier
Gemini 3.1 Flash-Lite	Google Gemini	1.0M	Free tier
Gemini 2.5 Flash	Google Gemini	1.0M	Free tier

Typical Use Cases

Gemini 3 Flash (Preview) use cases

Chat

Gemini 3 Flash (Preview) is tagged for chat in this catalog and works with OpenAI-compatible client libraries.

FAQ

Gemini 3 Flash (Preview) free API FAQ

Is Gemini 3 Flash (Preview) free to use?

Gemini 3 Flash (Preview) appears in the free model catalog for Google Gemini, but its current endpoint availability should be confirmed with the provider before use.

What is the Gemini 3 Flash (Preview) model ID?

The model ID shown in this catalog is gemini-3-flash-preview.

What are the Gemini 3 Flash (Preview) free tier rate limits on Google Gemini?

The listed free tier limit is Preview limits. Limits can change per account tier, so confirm against the provider dashboard.

What context window does Gemini 3 Flash (Preview) support?

The listed context window is 1.0M tokens with up to 65K output tokens.

More about Gemini 3 Flash (Preview)

Gemini 3 Flash (Preview) — free model from Google Gemini.

For API keys, setup steps, and provider-level limits, see the Google Gemini provider page.