Category · 3 options
Choosing ai model api
The language model that writes the answers in an AI feature. Tokens are usually the biggest bill. Price your real prompt sizes, send easy requests to a small model, and check whether a free tier uses your data for training.
Free plans and prices
In Cuely's default order for the general case. Your needs change the order; see below.
| Tool | Free plan | Paid from | At 1,000 users |
|---|---|---|---|
| Gemini API The cheapest mid-size model of the three at the published profile, with a free tier to prototype on. | Free tier with free input and output tokens (rate-limited); free-tier content is used to improve Google's products. | 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). | $488/month |
| Claude API Strong at following instructions and answering from supplied documents, with a very cheap small model. | None | Haiku 5.5: $0.10 per million input tokens, $0.50 output (prompts up to 100k). Sonnet 5.5: $2 input, $10 output. Opus 5.5: $4 input, $20 output. Sonnet cache reads: $0.10 per million. | $650/month |
| OpenAI API The widest ecosystem of examples and libraries, with a very cheap small model. | None | gpt-6-luna: $0.10 per million input tokens, $0.50 output. gpt-6.1-sol: $2 input, $10 output. gpt-6-astra: $10 input, $50 output. | $650/month |
Best pick by need
From the published scores Cuely ranks with. Only needs where one tool clearly leads.
- keep costs as low as possible: Gemini API. 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.