Google Gemini pricing for enrichment
All 9 Google models OpenClay supports, listed most capable first, with what 1,000 enriched rows cost on each once search fees are included.
Updated August 2026
Google · 9 models · keys start with AIza
Most capable
Gemini 3.1 Pro
$2.18 per 1,000 rows
Lowest cost per row
Gemini 2.5 Flash-Lite
$0.08 per 1,000 rows
How Google bills web search
Gemini 3.x includes 5,000 free grounded searches per month, then $14 per 1,000. The 2.5 series gets 1,500 free per day but costs $35 per 1,000 after that, which usually makes a 3.x model cheaper overall despite a higher token price.
Worth knowing
Paste a Google Cloud service-account JSON instead of an API key to run through Vertex AI. Gemini 3.x on Vertex is only served from the global endpoint, which OpenClay handles automatically.
Every Gemini model
| Model | Input | Output | Context | Per 1k rows |
|---|---|---|---|---|
Gemini 3.1 Pro gemini-3.1-pro-preview Google's strongest reasoning with live search grounding | $2 | $12 | 1000k | $2.18 |
Gemini 3.6 Flash gemini-3.6-flash Latest Flash generation, cheaper output than 3.5 Flash | $1.5 | $7.5 | 1000k | $1.43 |
Gemini 3.5 Flash gemini-3.5-flash Generally available Flash, no preview caveats | $1.5 | $9 | 1000k | $1.64 |
Gemini 3 Flash gemini-3-flash-preview Strong quality at a fraction of flagship cost, great default | $0.5 | $3 | 1000k | $0.55 |
Gemini 3.5 Flash-Lite gemini-3.5-flash-lite Stable low-cost tier when you want GA over preview | $0.3 | $2.5 | 1000k | $0.43 |
Gemini 3.1 Flash-Lite gemini-3.1-flash-lite Large simple lookups, the lowest cost per row of any model here | $0.25 | $1.5 | 1000k | $0.27 |
Gemini 2.5 Pro gemini-2.5-pro Reproducing an earlier 2.5-era run | $1.25 | $10 | 1000k | $1.71 |
Gemini 2.5 Flash gemini-2.5-flash Reproducing an earlier 2.5-era run | $0.3 | $2.5 | 1000k | $0.43 |
Gemini 2.5 Flash-Lite gemini-2.5-flash-lite Lowest token price, but search costs 2.5x the 3.x models | $0.1 | $0.4 | 1000k | $0.08 |
Using your Google key
- Get a key from Google AI Studio. Keys start with
AIza. - Paste it into OpenClay. It stays in browser memory for the tab, never written to disk, a database, a log or a cookie.
- Test five rows for an exact per-row cost before running the batch.
- If you hit rate limits, lower the parallel-requests slider. Failed rows retry automatically with exponential backoff.
Compare against other providers
No account, no card, no platform fee.
Bring your own API key and pay the model provider directly.
Try Gemini on your data