gemini-3-flash-preview
Google · text, image, audio → text
gemini-3-flash-preview is Google's latest released, most balanced model, excelling in speed, scale, and cutting-edge intelligence.
Input$0.50 /M
Output$3.00 /M
← Modelsgemini-3-flash-previewgemini-3-flash-preview-free
gemini-3-flash-preview vs gemini-3-flash-preview-free
Context lengths are 1,048,576 tokens on gemini-3-flash-preview and 1,048,576 tokens on gemini-3-flash-preview-free. On the LMArena coding leaderboard gemini-3-flash-preview scores 1509 and gemini-3-flash-preview-free scores 1509.
gemini-3-flash-previewgemini-3-flash-preview-free+ Add model · 2/4
gemini-3-flash-preview-free
Google · text, image, audio, video → text
gemini-3-flash-preview-free is the free, publicly available version of gemini-3-flash-preview, offering the same model capabilities with usage limits in place to ensure service stability. Limits include up to 5 requests per minute, a maximum of 250 requests per day, and a daily quota of 500,000 tokens. Free usage is based on shared capacity and is limited in availability. This version is intended for testing and light usage; for consistent and reliable access, please switch to the paid model.
Input$0.00 /M
Output$0.00 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
gemini-3-flash-preview
gemini-3-flash-preview-free
Input /M
$0.50
$0.00
Output /M
$3.00
$0.00
Cache read /M
$0.05
$0.00
Context length
1,048,576
1,048,576
Max output
0
65,536
Time to First Token
6.6 s
-
Throughput
160.4 tok/s
-
Modalities
textimageaudio
textimageaudiovideo
Supported Parameters
thinkingwebtoolsfunction callingstructured outputs
toolsfunction callingstructured outputsthinking
API Formats
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
gemini-3-flash-previewgemini-3-flash-preview-free
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
gemini-3-flash-previewgemini-3-flash-preview-free
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
gemini-3-flash-previewgemini-3-flash-preview-free
144014801520
Overall
14731473
Coding
15091509
Math
14761476
Hard prompts
14921492
Instruction following
14581458
Multi-turn
14831483
Creative writing
14591459
Longer query
14751475
Chinese
15211521
English
14751475
Vision
gemini-3-flash-previewgemini-3-flash-preview-free
124012801320
Overall
12711271
OCR
12851285
Diagram
12961296
Homework
13141314
WebDev Arena
gemini-3-flash-previewgemini-3-flash-preview-free
138014201460
Overall
14371437
React
14301430
HTML
14401440
Gaming
14521452
Simulations
14171417
Data analytics
14131413
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
gemini-3-flash-preview-free
$0.00 /mo
gemini-3-flash-preview
$75.00 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
How do their coding arena scores compare?
gemini-3-flash-preview: 1509; gemini-3-flash-preview-free: 1509 (LMArena coding leaderboard).
How large is each context window?
gemini-3-flash-preview accepts 1,048,576 and gemini-3-flash-preview-free accepts 1,048,576 input tokens.
What inputs and capabilities does each model support?
gemini-3-flash-preview accepts text, image and audio input and supports thinking, web search, tool calling, function calling and structured outputs; gemini-3-flash-preview-free accepts text, image, audio and video input and supports tool calling, function calling, structured outputs and thinking.
Can I call gemini-3-flash-preview and gemini-3-flash-preview-free with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
AIHubMix