Gemini 3 Flash Preview on QuickSilver Pro
Gemini 3 Flash Preview remains available only for compatibility with existing integrations. Migrate production and new workloads to gemini-3.6-flash, Google's current GA Flash model.
At a glance
Temporary compatibility for integrations migrating to Gemini 3.6 Flash.
Pricing comparison ($/1M tokens)
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.425 | $2.55 | lowest-cost |
| OpenRouter (google/gemini-3-flash-preview) | $0.50 | $3.00 | 15% lower |
| OpenAI (GPT-4o-mini) | $0.15 | $0.60 | 325% more expensive |
When to use
Pick 3 Flash Preview when Flash Lite isn't smart enough but 3.1 Pro is overkill: harder coding turns in an agentic loop, multi-step analysis, long-context summarization with non-trivial cross-document reasoning. The output price is still ~4× lower than 3.1 Pro Preview.
When to use something else
For revenue-critical production paths, prefer a Gemini GA model (3.5 Flash) until 3 Flash is promoted — preview semantics can change. For low-cost high-volume chat, 3.1 Flash Lite at $0.2125/$1.275 is much lower. For top-tier reasoning, escalate to 3.1 Pro Preview ($1.70/$10.20) or DeepSeek V4 Pro ($0.435/$0.87).
Quickstart (curl)
curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-flash-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'OpenAI-compatible. One-line migration via base_url.
FAQ
Preview means Google can change output formats, thinking behavior, or pricing without prior notice. For prototyping and A/B evals, ship today. For paths where a behavior shift would break customers, gate behind a feature flag and pin to 3.5 Flash GA as the fallback until Google labels 3 Flash as GA.
3 Flash Preview is the lower, preview-tier Flash ($0.425/$2.55 per 1M tokens); 3.5 Flash is the GA step up ($1.275/$7.65) with stronger reasoning and committed-stable behavior. Use 3 Flash Preview for cost-sensitive prototyping and evals; move to 3.5 Flash GA when you need production stability. Run a side-by-side eval on your traffic before committing.
QuickSilver Pro lists Gemini 3 Flash Preview at $0.425 input / $2.55 output per 1M tokens — ~15% below Vertex retail and OpenRouter's $0.50/$3.00. OpenAI-compatible API; switch from another provider with a base_url + key swap on the OpenAI SDK.