text
Gemini 2.5 Pro
silvamux/
gemini-2.5-proGemini 2.5 Pro is Google's multimodal thinking model with long context and native tool calls, strong in multilingual, mathematical and analytical work — suited to research, translation and content review.
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 | $1.25 | $10 | $0.125 | $0 |
| > 200K tokens | $2.5 | $15 | $0.25 | $0 |
Capabilities
Gemini 2.5 Pro scored 72 overall, performing well — a multimodal thinker built for long context. It stands out in multilingual capability (86%), math and science reasoning (85%) and general knowledge (82%), handling cross-language material and rigorous analysis over long documents, which serves translation and content moderation well. Comparatively, agent collaboration (56%) is weak; tool-orchestration workflows are a stretch. Long-document multilingual analysis is its sweet spot.
72/ 100
Advanced Capabilities
8 itemsAgent Collaboration56%
18 questions · Mixed
Code Generation56%
12 questions · Objective
Code Comprehension & Debugging63%
6 questions · Mixed
Creative Writing65%
22 questions · Subjective
Information Retrieval / RAG66%
9 questions · Mixed
Long-Context Handling76%
16 questions · Subjective
Math & Science Reasoning85%
14 questions · Mixed
Multilingual Capability86%
11 questions · Subjective
General Foundations
3 itemsGeneral Knowledge82%
10 questions · Mixed
Text Comprehension77%
23 questions · Subjective
Logical Reasoning69%
16 questions · Mixed
Safety & Compliance
2 itemsHallucination Control75%
15 questions · Subjective
Instruction Following75%
18 questions · Subjective
Performance
Gemini 2.5 Pro
gemini-2.5-proLast 24 hours · 36,433 requests
- First token · TTFT · P50
- 1138ms P95 2055 ms
- Output speed · TPS · P50
- 49tok/s P95 83 tok/s
- Full response · E2E · P50
- 7.34s P95 9.09 s
- Request success rate
- 97.19% 35,411 completed requests
24-hour availability
24 hours ago12 hours agoNow
Gemini 2.5 Pro example code and API
Pro
gemini-2.5-pro/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-2.5-pro",
"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-2.5-pro",
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-2.5-pro\",\"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-2.5-pro',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)