gemini-3.7-flash pricing and API access
Run gemini-3.7-flash through Code By AI for $0.10 per 1M input tokens and $0.30 per 1M output tokens. Google lists the same model at $1.00 and $3.00; you pay about 90% less than that, with no monthly subscription.
Official price
$1.00
per 1M tokens, USD
Your price
$0.10
per 1M tokens, USD
Δ
−90%
1/10 of official price
| gemini-3.7-flash | Official price | Your price |
|---|---|---|
| Input | $1.00 | $0.10 |
| Cached input | $0.10 | $0.01 |
| Output | $3.00 | $0.30 |
How to use gemini-3.7-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-3.7-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-3.7-flash FAQ
- How much does gemini-3.7-flash cost on Code By AI?
- gemini-3.7-flash costs $0.10 per 1M input tokens, $0.01 per 1M cached input tokens and $0.30 per 1M output tokens. Google lists the same model at $1.00 input and $3.00 output.
- Is gemini-3.7-flash the default Gemini model?
- No. Requests to Gemini without a model parameter use the default model instead; set the model parameter to gemini-3.7-flash to select this one.
- How do I use gemini-3.7-flash?
- Export GOOGLE_GEMINI_BASE_URL=https://www.codebyai.net/api/agent and GEMINI_API_KEY in your shell, pass the model ID gemini-3.7-flash, then launch the CLI. The Gemini guide covers the full configuration.