text
Gemini 3.1 Pro Preview
silvamux/
gemini-3.1-pro-previewGemini 3.1 Pro is Google's new professional model with broad knowledge and multilingual strength, handling long-form and structured content — suited to localization, scriptwriting and e-commerce copywriting.
Pricing
Tiers are determined by the input context length of each request; Tune and Pro share the same tiered prices.
| Input context | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| ≤ 200K tokens | $2 | $12 | $0.2 | $2 |
| > 200K tokens | $4 | $18 | $0.4 | $4 |
Capabilities
Gemini 3.1 Pro scored 74 overall, performing well — a content-oriented professional model. It stands out in general knowledge (92%), multilingual capability (89%) and instruction following (87%), producing well-structured multilingual content to spec, which suits translation, scriptwriting and e-commerce copy. Comparatively, code comprehension and debugging (40%) is markedly weak — coding tasks are effectively a blind spot. Structured, multilingual content work is where it performs.
74/ 100
Advanced Capabilities
8 itemsAgent Collaboration59%
18 questions · Mixed
Code Generation42%
12 questions · Objective
Code Comprehension & Debugging40%
6 questions · Mixed
Creative Writing77%
22 questions · Subjective
Information Retrieval / RAG74%
9 questions · Mixed
Long-Context Handling83%
16 questions · Subjective
Math & Science Reasoning77%
14 questions · Objective
Multilingual Capability89%
11 questions · Subjective
General Foundations
3 itemsGeneral Knowledge92%
10 questions · Mixed
Text Comprehension80%
23 questions · Subjective
Logical Reasoning74%
16 questions · Mixed
Safety & Compliance
2 itemsHallucination Control83%
15 questions · Mixed
Instruction Following87%
18 questions · Subjective
Performance
Gemini 3.1 Pro Preview
gemini-3.1-pro-previewLast 24 hours · 78,887 requests
- First token · TTFT · P50
- 595ms P95 1715 ms
- Output speed · TPS · P50
- 32tok/s P95 32 tok/s
- Full response · E2E · P50
- 4.46s P95 9.55 s
- Request success rate
- 98.01% 77,319 completed requests
24-hour availability
24 hours ago12 hours agoNow
Gemini 3.1 Pro Preview example code and API
Pro
gemini-3.1-pro-preview/api/v0/chat/completions/api/v1/chat/completionscurl https://silvamux.io/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-pro-preview",
"messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
}'# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://silvamux.io/api/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="gemini-3.1-pro-preview",
messages=[
{"role": "user", "content": "Hello, please introduce yourself"}
],
)
print(response.choices[0].message.content)// Gradle: implementation(__HL_SLOT_0__)
import okhttp3.*;
OkHttpClient client = new OkHttpClient();
MediaType json = MediaType.get("application/json");
String payload = "{\"model\":\"gemini-3.1-pro-preview\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello, please introduce yourself\"}]}";
Request request = new Request.Builder()
.url("https://silvamux.io/api/v1/chat/completions")
.header("Authorization", "Bearer YOUR_API_KEY")
.post(RequestBody.create(payload, json))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}// npm install openai
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://silvamux.io/api/v1',
apiKey: 'YOUR_API_KEY',
})
const response = await client.chat.completions.create({
model: 'gemini-3.1-pro-preview',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)