Gemini 3.5 Flash-Lite on QuickSilver Pro
Gemini 3.5 Flash-Lite is Google's current low-cost GA model for high-throughput workloads. QuickSilver Pro serves it with a 1M-token context window at $0.255 input / $2.125 output per million tokens, 15% below Google's $0.30/$2.50 list price.
At a glance
High-volume Gemini workloads with GA stability and predictable cost.
Pricing comparison ($/1M tokens)
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.255 | $2.125 | lowest-cost |
| Google list price (google/gemini-3.5-flash-lite) | $0.30 | $2.50 | 15% lower |
| OpenAI (GPT-4o mini) | $0.15 | $0.60 | 254% more expensive |
When to use
Use Gemini 3.5 Flash-Lite for classification, extraction, routing, summarization, simple chat, and agent subtasks where throughput and price matter most.
When to use something else
For reasoning-heavy coding or multimodal analysis, use Gemini 3.6 Flash. For the hardest long-context reasoning tasks, evaluate Gemini 3.1 Pro Preview.
Quickstart (curl)
curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash-lite",
"messages": [{"role": "user", "content": "Hello!"}]
}'OpenAI-compatible. One-line migration via base_url.
FAQ
Yes. Existing integrations can continue using the old ID during migration, but new workloads should use gemini-3.5-flash-lite.
QuickSilver Pro charges $0.255 input and $2.125 output per 1M tokens, 15% below Google's $0.30/$2.50 list price.
Yes. Use https://api.quicksilverpro.io/v1 as the base URL and gemini-3.5-flash-lite as the model ID.