- 1M context
- Multimodal
- Reasoning
- Responses API
Gemini 3.6 Flash on QuickSilver Pro
Gemini 3.6 Flash is Google's current general-purpose Flash GA model with a 1M-token context window. QuickSilver Pro serves it through one OpenAI-compatible endpoint at $0.6375 input / $3.1875 output per million tokens, 15% below Google's $0.75/$3.75 list price.
- 1M context
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$0.6375 / $3.1875
15% lower
on both legs vs Google list price
Pricing comparison ($/1M tokens)
Bar length = price relative to the highest price shown
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.6375 | $3.1875 | lowest-cost |
| Google list price(google/gemini-3.6-flash) | $0.75 | $3.75 | 15% lower |
| OpenAI (GPT-4o) | $2.50 | $10.00 | 68% lower |
Google list source: ai.google.dev/gemini-api/docs/pricing
At a glance
- Context
- 1M tokens
- Input / 1M
- $0.6375
- Output / 1M
- $3.1875
- Thinks by default
- Yes
- Latency · live
- —
- AA Intelligence Index
- 40
The recommended Gemini Flash for new production integrations.
When is Gemini 3.6 Flash the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Default to Gemini 3.6 Flash for production chat, multimodal analysis, coding, agent turns, and long-context workloads that need current Flash quality and GA stability.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Multi-step reasoning, on by default
When to use something else
For high-volume classification and extraction where price matters more than reasoning depth, use Gemini 3.5 Flash-Lite. For harder flagship reasoning, use Gemini 3.1 Pro Preview after evaluating preview stability.
- Output price matters mostGemini 3.5 Flash-Lite costs 0.667× this model’s output price and keeps the 1M context.Gemini 3.5 Flash-Lite $0.255 / $2.125 · 1M
- The task needs a stronger modelGemini 3.8 Flash scores 47 on the AA Intelligence Index (40 here), at 1× the output price.Gemini 3.8 Flash $0.6375 / $3.1875 · 1M
Quickstart (curl)
Get an API key →curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.6-flash",
"messages": [{"role": "user", "content": "Hello!"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="gemini-3.6-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.quicksilverpro.io/v1",
apiKey: process.env.QSP_KEY,
});
const response = await client.chat.completions.create({
model: "gemini-3.6-flash",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.quicksilverpro.io/v1/responses \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.6-flash",
"input": "Hello!"
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="gemini-3.6-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)OpenAI-compatible. One-line migration via base_url.
Gateway behavior
Compatibility notes for this model.
prompt- Prompts up to 1M tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Supported
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- $0.75 / $3.75ai.google.dev/gemini-api/docs/pricing
- Catalog verified
usage.cost = prompt_tokens × $0.6375/1M + completion_tokens × $3.1875/1M
FAQ
Common questions
Yes. Keep the preview ID only while you migrate existing integrations. New workloads should use gemini-3.6-flash, Google's current GA Flash model.
It costs $0.6375 input and $3.1875 output per 1M tokens, 15% below Google's $0.75/$3.75 list price.
Yes. Point the OpenAI SDK at https://api.quicksilverpro.io/v1 and set model to gemini-3.6-flash.