Gemini API Pricing — KeyoAPI vs Typical Google List Rates

Looking up Gemini API pricing usually means you already want Google-class models but need clearer unit economics — or a relay that also hosts paid DeepSeek IDs and Whisper under one balance. This page lists current Keyo catalog Gemini-class IDs with indicative sell rates on an OpenAI-compatible gateway.

Gemini API Pricing is a model-family pricing lane on KeyoAPI — a prepaid AI API gateway where one Bearer key and one wallet ($1 = 500,000 quota units) cover chat, speech, vision, OCR and video models.

Price comparison table

Indicative figures for planning. Confirm live Keyo sell rates on interactive Model Square or the static pricing list.

A gift-credit prototyping lane on the same key

Google Gemini free tiers are usually quota- or trial-shaped. On the same Keyo key you can call Atria-dawn-v2:free and other gift-credit catalog IDs on the gift-credit models page — gift-credit IDs that bill at dedicated gift-credit rates from your one-time $10 new-user credit (fair-use rate limits apply). Prototype there, then meter paid Gemini-class traffic.

Rates and how to call

Engineers comparing Gemini API pricing usually already want Google-class models with clearer unit economics — or one prepaid balance across Gemini-class IDs plus DeepSeek, GLM, Whisper, OCR, and TTS. Official Google surfaces win on brand trust; KeyoAPI wins when you want that stack without five invoices.

Keyo rates above are indicative sell prices from the live Keyo catalog. Always confirm interactive pricing pages under the pricing page (Model Square) before contracting volume. Catalog IDs can change as Google ships new stables — this page tracks what Keyo currently lists.

How to call: set OPENAI_BASE_URL=https://www.keyoapi.xyz/v1, use your Keyo API key, and pass the Gemini model string (for example gemini-3.8-flash) to POST /v1/chat/completions (for video models gemini-omni-1.1-flash and -ext, use POST /v1/videos/generations as detailed in the full pricing list and the API handbook). Many Google-native features remain Google-console only; Keyo focuses on OpenAI-compatible chat access for overseas developer stacks.

When Gemini list prices spike your margin, keep Gemini for multimodal strengths and shift plain text volume to deepseek-v4.1-flash or gpt-6-luna on the same key. For pure free prototyping, start on the gift-credit models page, then promote to Gemini paid IDs when quality gates pass.

Gemini 4 API: Argon and Barium

The Gemini 4 family entry is Gemini 4 API on KeyoAPI. It links to the gemini-4-argon model page and the gemini-4-barium model page, both already listed in the model guides page. Use one of those exact model IDs for POST /v1/chat/completions. The checked default-group rates are $0.7353 input and $3.6765 output per million tokens for either ID. A bare gemini-4 is a family label, not a model listed in the checked catalog.

curl https://www.keyoapi.xyz/v1/chat/completions \
  -H "Authorization: Bearer $KEYO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-4-barium","messages":[{"role":"user","content":"Hello"}]}'

Get started in five steps

1. Create an account — new users receive $10 of gift credit for prototyping.
2. Create an API key in the console.
3. Point your OpenAI SDK at https://www.keyoapi.xyz/v1 with the model ID from this page, or call the dedicated REST path from the API handbook.
4. Track spend in the console Wallet — $1 equals 500,000 quota units, and gift credit burns before recharged balance.
5. Set a per-key spending cap before wiring production traffic.

A verified first call is the acceptance test for the setup: the response should carry the payload shape documented in the handbook, the Wallet ledger should show a deduction in quota units (500,000 units = $1), and repeated calls should deduct linearly at the listed rate. Any mismatch usually means the model ID or endpoint is wrong — check both against the pricing list before debugging client code.

FAQ

Also see the model comparison page, the gift-credit models page, the full pricing list, and gemini-3.8-flash · gemini-3.7-flash.