Gemini 3.1 Flash-Lite (preview) is the preview channel of Google's low-latency, cost-effective multimodal model optimized for high-frequency, lightweight tasks, which Google positions as frontier-class performance rivaling larger models at a fraction of the cost.
- Input
- text image video audio $0.25/M
- Output
- text $1.5/M
- Audio input
- $0.75/M
- Context
- 1M
- vs GPT-4o
- ~95% cheaper
- Knowledge cutoff
- 2025-01
Benchmarks
Vendor-published: Alibaba (Qwen) Anthropic ByteDance Google 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 |
Thinking
| Parameter | reasoning_effort |
|---|---|
| Values | minimal · low · medium · high accepted set is the provider's |
Model
| Modalities | text + image + video + audio → text |
|---|
- DEPRECATED: shut down 2026-05-25
- migrate to gemini-3.1-flash-lite
- was the first Flash-Lite in the Gemini 3 series
One prompt, measured through the gateway
Gemini 3.1 Flash-Lite passed · 3 sentences
Enabling reasoning models increases your costs because the system now generates a significantly higher volume of "hidden" chain-of-thought tokens required to process complex logic. Since you are billed for every token produced during this internal deliberation phase, your total output volume has expanded alongside the depth of the analysis. You are essentially paying for the model to "think out loud" before arriving at a final answer, which directly scales your operational expenditure.
out 86 tok latency 1.4 s
Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.
Gemini 3.1 Flash-Lite passed · 8/8 cases
### Fixed Code ```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` ### Explanation of the Bug The original function failed because it initialized `best` and `cur` to `0` and effectively counted "transitions" (how many times an element matched its predecessor) rather than the total count of elements in a run. By starting at `0`, a single-element list returned `0` instead of `1`, and because `cur` reset to `0` and only incremented when a match was found, the function effectively counted "extra" matches beyond the first element, failing to account for the initial element of any run. […]
out 271 tok latency 2.0 s
Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.
Gemini 3.1 Flash-Lite passed · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": null, "guidance": null } ```
out 56 tok latency 1.3 s
Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.
Gemini 3.1 Flash-Lite passed · 125 words, 0 banned, 1 question
We are launching a new caching layer for our API gateway that stores LLM responses across multiple providers. By capturing frequently requested prompts, this feature significantly lowers latency and reduces operational costs for your applications. Instead of querying expensive models for repetitive tasks, your system retrieves identical outputs instantly from our high-speed cache. This integration maintains consistency while supporting diverse provider workflows, ensuring your infrastructure remains both efficient and scalable. Are you ready to optimize your token usage and improve response times for every user? Configuration takes only minutes through our existing dashboard. This addition provides a practical strategy to manage API spend without sacrificing performance or quality. […]
out 140 tok latency 2.3 s
Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.
Use Gemini 3.1 Flash-Lite 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-3.1-flash-lite-preview",
messages=[{"role": "user", "content": "Summarize this diff"}],
)
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-3.1-flash-lite-preview",
messages: [{ role: "user", content: "Summarize this diff" }],
});
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-3.1-flash-lite-preview",
"messages": [{"role": "user", "content": "Hello"}]
}'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-3.1-flash-lite-preview",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gemini-3.1-flash-lite-preview")
.addUserMessage("Summarize this diff")
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About Gemini 3.1 Flash-Lite
- Released in March 2026 as the first Flash-Lite in the Gemini 3 series, it takes text, image, video, audio, and PDF input within a 1,048,576-token context window and 65,536-token output limit, and returns text.
- Recommended uses include translation, transcription, data extraction, summarization, and model routing, the same high-throughput, cost-sensitive band the Lite tier has always targeted.
- It supports function calling, structured outputs, code execution, Search and Maps grounding, URL context, file search, context caching, the Batch API, and Flex and Priority inference; computer use, the Live API, and image or audio generation are not supported.
- Thinking is set with the thinking_level string rather than a numeric budget, and because minimal is the floor on Gemini 3 rather than an off switch, reasoning tokens are billed on every call; thought signatures must be echoed back to keep multi-turn reasoning coherent.
- Google has since deprecated this preview identifier and points new work at the generally available gemini-3.1-flash-lite, so treat it as a pinned snapshot rather than a long-term target.
- Synthorai makes it callable through its OpenAI-compatible chat endpoint.
FAQ
Is the Gemini 3.1 Flash-Lite API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.25/M input tokens, that credit alone covers roughly 500 requests of ~8K tokens against Gemini 3.1 Flash-Lite.
What is Gemini 3.1 Flash-Lite best at?
Frontier-class performance at a fraction of cost; configurable thinking levels before answering; built for translation, extraction, and routing. See the About section for the full picture from the vendor's own release notes.
How much does Gemini 3.1 Flash-Lite cost?
Gemini 3.1 Flash-Lite costs $0.25 per million input tokens and $1.5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup.
Does Gemini 3.1 Flash-Lite support prompt caching?
Gemini 3.1 Flash-Lite has no cache-read discount on Synthorai today. Prompt caching still applies to other models on the gateway; see the pricing table for cache-enabled alternatives. Provider caching comparison →
How do I get access to Gemini 3.1 Flash-Lite?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3.1-flash-lite-preview", and you're done. One API key covers every model on the gateway.
What is Gemini 3.1 Flash-Lite's knowledge cutoff?
Gemini 3.1 Flash-Lite'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.