New Sign up free, 10 calls on us. Up to $1, no card needed.

Gemini 3 Flash

Released 2025-12-17

chatVisionCodeTool callingReasoningimagePrompt caching

Gemini 3 Flash (preview) is the model Google's documentation describes as the best in the world for multimodal understanding and its "most powerful agentic and vibe-coding model yet," launched with the promise of frontier-class performance that rivals larger models at a fraction of the cost.

Input
text image video audio $0.5/M
Output
text $3/M
Audio input
$1/M
Cache read
$0.05/M
Context
1M
vs GPT-4o
~90% cheaper
Knowledge cutoff
2025-01

Benchmarks

Above average7 / 16
Gemini 3 Flash other models measured peer average no peer scored higher
ResearchRubrics
36.9%
GPQA Diamond
90.7%
BrowseComp
41.5%
Video-MME (w. sub)
85.2%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance Google MiniMax Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 60 comparable models

Input$0.5/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$3/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.05/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,048,576
Max output (vendor spec) 65,536
Knowledge cutoff 2025-01

Prompt caching

How it caches automatic + explicit
Min prefix 4,096

Thinking

Vendor control thinkingLevel
Accepted values minimal · low · medium · high
Default high applied when the request sets nothing
Can be turned off No
Thinking behaviour Google states Gemini 3 Flash does not support full thinking-off, so minimal is a floor rather than a switch and thinking tokens bill as output tokens on every request; thought signatures should be echoed back and are required for function calling.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image + video + audio → text
  • Preview model
  • 1,048,576-token input
  • computer use supported
  • image generation NOT supported despite gateway capability tag

per Google official docs ↗

Use Gemini 3 Flash in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Gemini 3 Flash

  • It accepts text, image, video, audio, and PDF input within a 1,048,576-token context window and produces up to 65,536 output tokens.
  • Capabilities include function calling, structured outputs, code execution, computer use, Search and Maps grounding, URL context, file search, context caching, the Batch API, and Flex and Priority inference.
  • Thinking is controlled by thinking_level, which accepts minimal, low, medium, and high and defaults to high, the most expensive default in the family: on every Gemini 3 model minimal is a floor rather than an off switch, so thinking tokens are billed on each request.
  • The generation also introduced thought signatures, encrypted traces of internal reasoning that have to be returned to preserve multi-turn continuity, alongside new media-resolution controls, both of which are migration work rather than optional extras when moving up from 2.5.
  • As a preview channel it carries no stability guarantees; Google's stable successor is gemini-3.5-flash, whose model page lists this ID as its preview alias.
  • Synthorai offers it via its unified OpenAI-compatible chat completions interface.

FAQ

Is the Gemini 3 Flash API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.5/M input tokens, that credit alone covers roughly 250 requests of ~8K tokens against Gemini 3 Flash.

What is Gemini 3 Flash best at?

Described as best for multimodal understanding; state-of-the-art reasoning with creative-coding strength; computer use and Maps grounding support. See the About section for the full picture from the vendor's own release notes.

How much does Gemini 3 Flash cost?

Gemini 3 Flash costs $0.5 per million input tokens and $3 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.05/M.

Does Gemini 3 Flash support prompt caching?

Yes: automatic caching is on by default, with an explicit mode for guaranteed savings. Cached input tokens bill at $0.05/M vs $0.5/M uncached; prompts need a 4,096-token stable prefix to cache. Prompt caching guide →

How do I get access to Gemini 3 Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3-flash-preview", and you're done. One API key covers every model on the gateway.

What is Gemini 3 Flash's knowledge cutoff?

Gemini 3 Flash's knowledge cutoff is 2025-01, per the vendor's official documentation (as of 2026-07-09).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →