AI model API · facts read November 7, 2026
Gemini API
Google's model API (Gemini Flash and Pro models). The cheapest mid-size model of the three at the published profile, with a free tier to prototype on.
- Free plan
- Free tier with free input and output tokens (rate-limited); free-tier content is used to improve Google's products.
- Paid from
- Gemini 3.8 Flash: $0.75 per million input tokens and $3.75 output through December 31, 2026, then $1.50 and $7.50 from January 1, 2027. Gemini 3.1 Pro Preview: $2.00 input, $12.00 output (prompts up to 200k tokens).
- Monthly cost at 1,000 users
- $488/month Gemini 3.8 Flash from January 1, 2027: 200M input × $1.50 + 25M output × $7.50 per million = $487.50 ($243.75 at the price through December 31, 2026). Use the paid tier for customer data.
- Free plan allows commercial use
- Not stated
- Open source
- No
- Self-hostable
- No
Source: Gemini API pricing, read November 7, 2026. Prices change; check the vendor's page before you commit.
Best for
- Keeping token cost down
- Prototyping on a free tier
- Long documents
Watch out for
- On the free tier, the pricing page says content is used to improve Google's products; on the paid tier it is not. Don't send customer data on the free tier.
- Gemini 3.8 Flash's price doubles on January 1, 2027 (to $1.50 input and $7.50 output per million tokens).
- Gemini 3.1 Pro is listed as a preview model.
How Cuely scores Gemini API
The published scores, from −3 to +3, that decide when Cuely picks it. Method
- +2keep costs as low as possible. Gemini 3.8 Flash is about $488 a month at the profile from January 2027 ($244 until then), the lowest of the three mid-size models.
- +1answers over the user's own documents. Large context windows make it easy to pass long retrieved passages.
- −1regulated or compliance-sensitive. The free tier trains on your content; regulated data must stay on the paid tier.