Gemini 2.5 FlashAPI
Previous-gen Gemini Flash — extreme value.
Prezzo input
$0.09
per 1M tokens
Prezzo output
$0.75
per 1M tokens
Prompt caching
Passa cache_control sui prefix stabili — gli hit di cache vengono fatturati a una frazione del prezzo di input. Le scritture di cache restano alla tariffa di input normale.
Calcolato automaticamente come input × 0.2
Specifiche
- ID modello
gemini-2-5-flash- Endpoint
POST /v1/chat/completions- Categoria
- Text
- Provider
- Capability
- visionfunctionstreaming
Compatibilità OpenAI drop-in
Punta il tuo SDK OpenAI esistente a api.kunavo.com/v1 e sostituisci l'ID del modello. Niente cambi di streaming, nessun nuovo SDK.
Vedi la docGemini API pricing guideProvalo tu stesso
Imposta KUNAVO_API_KEY da /app/keys ed esegui lo snippet sotto.
curl https://api.kunavo.com/v1/chat/completions \
-H "Authorization: Bearer $KUNAVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-2-5-flash",
"messages": [
{"role": "user", "content": "Hello, Gemini 2.5 Flash"}
],
"stream": false
}'FAQ
How much does Gemini 2.5 Flash cost?
On Kunavo, Gemini 2.5 Flash is $0.09 per 1M input tokens and $0.75 per 1M output tokens — about 70% under Google's official price. Failed requests are never billed, and it's pay-as-you-go — you only pay for successful calls.
Can I call Gemini 2.5 Flash with the OpenAI SDK?
Yes. Set base_url to https://api.kunavo.com/v1, pass your Kunavo key, and set model to "gemini-2-5-flash". Requests and responses are OpenAI-compatible.
What endpoint does Gemini 2.5 Flash use?
Gemini 2.5 Flash is called via POST /v1/chat/completions on Kunavo's OpenAI-compatible API.
What is Gemini 2.5 Flash good for?
Gemini 2.5 Flash is a text model from Google, with support for vision, function, streaming.