Loading…
LLM · Google
Google's fast, low-cost Gemini model for chat, reasoning and image understanding. OpenAI-compatible API, billed per token — you pay only for tokens used.
$0.27 in · $1.35 out / 1M tokens
No samples yet
We're generating our own sample outputs for this model — try it yourself in the Playground.
# Gemini 3.8 Flash Fast, affordable Gemini model for chat, summarisation, extraction and image understanding, with adjustable reasoning (`reasoning_effort`: low or high). - **Context:** up to 1M tokens · **Output:** up to 65,536 tokens per reply - **Input:** text and images (https URLs or base64 data URLs) - **Billing:** per token. Reasoning (thinking) tokens count as output. Each request reserves its maximum cost and is charged only for what it used. Call it with any OpenAI SDK: set the base URL to the ANKY.AI API and use `POST /v1/chat/completions`.