google · GEMINI
Gemini 3.8 Flash API Pricing
Check the model ID and provider reference rates for Gemini 3.8 Flash, along with current pricing availability on GEMINI.
Effective GEMINI API rates
USD per 1M tokens. Quota rates use the current AI in IDE base price × 0.625. Provider prices as of 2026-11-02.
Due to recent official risk controls, the Gemini model service may be unstable. Please choose carefully.
| AI in IDE quota rate | Reference provider rate | |
|---|---|---|
| Input | $0.625 | $0.75 |
| Cache read | $0.0625 | $0.075 |
| Output | $1.875 | $3.75 |
Use Gemini 3.8 Flash in your client
Create a GEMINI API key in your dashboard, replace YOUR_DASHBOARD_API_KEY, and run this request in a Bash-compatible terminal. The key and its funding source need a positive balance; this request consumes quota.
curl --globoff 'https://api.aiinide.com/v1beta/models/gemini-3.8-flash:generateContent' \
-H "x-goog-api-key: YOUR_DASHBOARD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents":[{"role":"user","parts":[{"text":"Hello"}]}]}'Example: usage versus a top-up purchase
Each row uses a 3:1 input-to-output mix and no cache reads. Quota consumed is the cost of that mix. The top-up column is a separate purchase.
| Monthly tokens | Reference API cost | Quota this example consumes | Smallest top-up that covers it |
|---|---|---|---|
| 1M | $1.50 | $0.9375 | 62.5 dollars of quota, priced at $7.99 |
| 10M | $15.00 | $9.375 | 62.5 dollars of quota, priced at $7.99 |
| 100M | $150.00 | $93.75 | 93.75 dollars of quota, priced at $11.99 |
The quota column is what this token mix consumes. The top-up column is the smallest purchase the slider accepts: $62.5, then steps of $31.25. A small task does not cost that purchase. Examples round top-up quota up to the next $31.25 with a $62.5 minimum. Actual charges vary by usage, plan, context, speed, and promotions.
Protocol, channels, and tools
- Protocol
- Gemini generateContent
- Path
- /v1beta/models/gemini-3.8-flash:generateContent
- API key header
- x-goog-api-key
Channels and this model ID
- AWSQ is not compatible with this model ID.
- CCMAX is not compatible with this model ID.
- CODEX is not compatible with this model ID.
- GEMINI is compatible with this model ID and uses 0.625× the configured model price when the model is in the catalog.
Tool limits on this channel
Only client-side function declarations are accepted. Hosted tools, including Google Search, are rejected.
When to use Gemini 3.8 Flash
Google offers the following positioning as a starting point for model selection. This is the provider’s wording, not an AI in IDE evaluation or performance promise.
Gemini 3.8 Flash is our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
On this site, Gemini 3.8 Flash uses only the GEMINI channel. The public 0.625× multiplier applies to quota deductions at the site’s configured base prices; it is not a checkout price.
Only client-side function declarations are accepted. Hosted tools, including Google Search, are rejected.
Google’s official thinking-level guidance The official thinking levels are `low`, `medium`, `high`, with `medium` as the default. Google also states: `minimal` thinking level is not supported for Gemini 3.8 Flash and will return an error.
Gemini 3.8 Flash API FAQ
How much does Gemini 3.8 Flash API cost?
Reference rates for Gemini 3.8 Flash are USD 0.75 input, USD 0.075 cache read, and USD 3.75 output per 1M tokens. AI in IDE applies 0.625× its configured model price when charging quota.
What is the Gemini 3.8 Flash model ID?
The model ID is gemini-3.8-flash.
How do I use Gemini 3.8 Flash in my IDE?
Create a GEMINI API key, run the setup example on this page, and follow the linked IDE guide.