Gemini 3.1 Flash-Lite vs Gemini 3.7 Flash
何时使用哪一个 — 经过整理的结论，而非基准测试表格
这两款模型均具有 1048576 token 的上下文窗口、65536 token 的最大输出，以及相同的文本、图像、视频和音频输入及文本输出，因此两者的区别在于价格与推理：gemini-3.1-flash-lite-preview 的费用为每百万输入 $0.25 和输出 $1.5，而 gemini-3.7-flash 的输入收费为其 3 倍（$0.75），输出收费为其 2.5 倍（$3.75），并增加了推理能力标志。在成本优先的大批量多模态工作中，请选择 gemini-3.1-flash-lite-preview；对于需要推理的任务，或可适用其 $0.075 缓存读取费率的重复提示词任务，请选择 gemini-3.7-flash。
定价
| Gemini 3.1 Flash-Lite | Gemini 3.7 Flash | Δ | |
|---|---|---|---|
| 输入 / 1M tokens | $0.25 | $0.75 | 0.33× |
| 输出 / 1M tokens | $1.5 | $3.75 | 0.4× |
| 缓存读取 / 1M tokens | — | $0.075 | — |
费率取自构建时的实时目录；每个模型页面均附有当前的费率卡。
它们的位置 — 以该计费单位计费的所有 63 个 聊天 模型的 每 1M token 的输入价格（对数刻度）
能力
| Gemini 3.1 Flash-Lite | Gemini 3.7 Flash | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 是 —— 厂商未公布调节参数 | 是 —— 厂商未公布调节参数 |
| 结构化输出 | 是 | 是 |
| 提示词缓存 | 隐式 + 显式 | 隐式 + 显式 |
| 缓存生存时间 | 未公开 | 未公开 |
| 最小缓存前缀 | 4096 个 token | 4096 个 token |
规格
| Gemini 3.1 Flash-Lite | Gemini 3.7 Flash | |
|---|---|---|
| 输入模态 | 文本 图像 音频 视频 | 文本 图像 音频 视频 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-03-03 | 2026-08-13 |
| 知识截止日期 | 2025-01 | — |
| 上下文窗口 | 1M | 1M |
| 最大输出 | 66K | 66K |
规格转录自各供应商的文档；若供应商未发布某项数据，则直接省略该行，而非进行推断。 完整来源： Gemini 3.1 Flash-Lite · Gemini 3.7 Flash
单个 Prompt，两个模型 —— 通过网关实测
Gemini 3.1 Flash-Lite 通过 · 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.
输出 86 tok 延迟 1.4 s
Gemini 3.7 Flash 通过 · 3 sentences
Enabling reasoning causes the model to generate a high volume of invisible "thinking tokens" behind the scenes to deliberate and solve complex logic before delivering a final response. Because our vendor bills strictly on token volume, this additional internal computation effectively doubled our billable output per query. In short, our costs increased because we are now paying for the extra compute capacity required to produce significantly higher-accuracy answers.
输出 878 tok (+799 思考) 延迟 6.9 s
指令遵循（恰好三句，可数）、受众适配（面向 CFO 的语气），以及下方 token 计量所暴露的隐藏思考计费缺口。
Gemini 3.1 Flash-Lite 通过 · 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. […]
输出 271 tok 延迟 2.0 s
Gemini 3.7 Flash 通过 · 8/8 cases
Here is the corrected function: ```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 else: cur = 1 best = max(best, cur) return best ``` ### Explanation of the Bug The original function tracked equal adjacent transitions instead of the actual number of elements in a run, causing all non-empty run lengths to be undercounted by one (e.g., returning `0` instead of `1` for single-element lists because the loop never executes, and `1` instead of `2` for pairs). Initializing both `best` and `cur` to `1` (after handling empty inputs) and resetting `cur` to `1` on a mismatch ensures every individual element is counted as a valid run of at least length one.
输出 1050 tok (+827 思考) 延迟 6.4 s
修复是否真的正确（可运行）、解释的信息密度，以及在一个边界明确的任务上的 token 效率。
Gemini 3.1 Flash-Lite 通过 · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": null, "guidance": null } ```
输出 56 tok 延迟 1.3 s
Gemini 3.7 Flash 通过 · 5/5 fields, guidance "withheld"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": "withheld" } ```
输出 918 tok (+858 思考) 延迟 6.2 s
schema 服从度（不臆造字段）、幻觉压力（guidance 明确被暂缓给出），以及结构化输出路径的差异。
Gemini 3.1 Flash-Lite 通过 · 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. […]
输出 140 tok 延迟 2.3 s
Gemini 3.7 Flash 通过 · 120 words, 0 banned, 1 question
Why pay twice for identical AI queries simply because you routed them to different model vendors? Today, we introduce Universal Prompt Caching directly within our unified API gateway architecture. This capability stores repeated prompt contexts across OpenAI, Anthropic, and local models, instantly returning stored results to eliminate redundant computation fees. When your application sends an LLM request, the gateway inspects the payload, identifies semantic matches, and returns accurate cached responses in under ten milliseconds. Engineering teams can now slash inference latency by eighty percent while dramatically reducing monthly token expenditures across diverse production deployments. You retain complete privacy control, flexible cache eviction policies, and granular metrics through a single dashboard. Update your routing settings today to accelerate overall system performance.
输出 2858 tok (+2718 思考) 延迟 14.1 s
约束服从度（字数预算、禁用词表、唯一的那句问句）、文风指纹，以及长度控制。
只需一行代码即可在它们之间切换
两个 ID 都包含在下方的每个选项卡中 — 高亮显示的两行是唯一的修改。相同的端点，相同的密钥，相同的请求结构。
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",
# model="gemini-3.7-flash", # 取消注释此行，注释上一行
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",
// model: "gemini-3.7-flash", // 取消注释此行，注释上一行
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",
# "model": "gemini-3.7-flash", # 取消注释此行，注释上一行
"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",
// Model: "gemini-3.7-flash", // 取消注释此行，注释上一行
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")
// .model("gemini-3.7-flash") // 取消注释此行，注释上一行
.addUserMessage("Summarize this diff")
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));常见问题
Gemini 3.1 Flash-Lite 和 Gemini 3.7 Flash 哪个更便宜？
在 输入 / 1m tokens 方面，Gemini 3.1 Flash-Lite 更便宜（$0.25 对比 $0.75，相差 3.0×）。其他行可能得出相反的结论——上方表格提供了完整信息，实际成本取决于你的组合使用情况。
我可以在不进行两次集成的情况下，对 Gemini 3.1 Flash-Lite 和 Gemini 3.7 Flash 进行 A/B 测试吗？
可以。两者均通过同一个兼容 OpenAI 的端点提供服务，并使用同一把 API 密钥——切换只需更改一行模型字符串，因此你可以将一部分流量路由到各个模型并直接比较账单。
Gemini 3.1 Flash-Lite 和 Gemini 3.7 Flash 支持提示词缓存吗？
我们的信息流中仅列出了两者之一的缓存读取定价；如果缺少费率，则说明该提供商没有对缓存读取单独定价。