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
Vendor-published: Alibaba (Qwen) Anthropic ByteDance Google MiniMax Moonshot OpenAI Tencent Z.ai
Price in context
Where the price sits among 60 comparable models
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
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)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "gemini-3-flash-preview",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-flash-preview",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "gemini-3-flash-preview",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gemini-3-flash-preview")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));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.