A million tokens of context for the price of a rounding error.
- Tier
- flash
- relative cost band
- Context
- 1M
- tokens per request
- Included from
- Free
- free plan
- API credit
- $33–$86
- a month on Go
Last 24 hours
Status
Too few calls to judge
Success
—
Median latency
2862 ms
p95 latency
3797 ms
Requests
4
Plan access
Each plan grants real usage on a schedule set by the plan (weekly for every paid plan, monthly on Free). Advertised as official-API-equivalent credit for the month. A call to Gemini 3.8 Flash costs whatever tokens it actually used.
| Plan | Included | Multiplier | Per 7 days | API credit / mo |
|---|---|---|---|---|
| Free$0/mo | Yes | — | — | $3.75–$8.50 |
| Go$5/mo | Yes | 1× | $8.25–$21.50 | $33–$86 |
| Plus$25/mo | Yes | 5× | $41.25–$107.50 | $165–$430 |
| Pro$50/mo | Yes | 10× | $82.50–$215 | $330–$860 |
| Max$100/mo | Yes | 20× | $165–$430 | $660–$1720 |
Call it
The endpoint speaks the OpenAI chat completions protocol, so any client you already have works once you change the base URL and the key.
curl https://ai.eaon.dev/v1/chat/completions \
-H "Authorization: Bearer $EAON_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eaon/gemini-3.8-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'