gemini-3.8-flash pricing and API access
Run gemini-3.8-flash through Code By AI for $0.08 per 1M input tokens and $0.38 per 1M output tokens. Google lists the same model at $0.75 and $3.75; you pay about 90% less than that, with no monthly subscription.
Official price
$0.75
per 1M tokens, USD
Your price
$0.08
per 1M tokens, USD
Δ
−90%
1/10 of official price
| gemini-3.8-flash | Official price | Your price |
|---|---|---|
| Input | $0.75 | $0.08 |
| Cached input | $0.08 | $0.0075 |
| Output | $3.75 | $0.38 |
How to use gemini-3.8-flash
Export GOOGLE_GEMINI_BASE_URL=https://www.codebyai.net/api/agent and GEMINI_API_KEY=sk-proj-xxxx, then launch the CLI, and use the model ID gemini-3.8-flash. The Gemini guide walks through the full configuration.
export GOOGLE_GEMINI_BASE_URL="https://www.codebyai.net/api/agent" export GEMINI_API_KEY="sk-proj-xxxx"Read the Gemini setup guide
Compare other Gemini models
gemini-3.8-flash FAQ
- How much does gemini-3.8-flash cost on Code By AI?
- gemini-3.8-flash costs $0.08 per 1M input tokens, $0.0075 per 1M cached input tokens and $0.38 per 1M output tokens. Google lists the same model at $0.75 input and $3.75 output.
- Is gemini-3.8-flash the default Gemini model?
- No. Requests to Gemini without a model parameter use the default model instead; set the model parameter to gemini-3.8-flash to select this one.
- How do I use gemini-3.8-flash?
- Export GOOGLE_GEMINI_BASE_URL=https://www.codebyai.net/api/agent and GEMINI_API_KEY in your shell, pass the model ID gemini-3.8-flash, then launch the CLI. The Gemini guide covers the full configuration.