Gemini 3.8 Flash

Google's current Flash model for everyday apps and agents: text, image, audio, video and PDF input, 1M-token context.

Gemini 3.8 Flash is Google's current Flash model, the one it recommends starting with for everyday apps and agents. Send a prompt, or a chat history in messages, and get a text answer. It reads images in the chat (image_url parts) and takes audio, video and PDF on the Google API route, inline or by a public URL. It takes up to 1.05M tokens of context and writes up to 65K tokens per answer.

Set reasoning_effort to low, medium or high (medium when you send none). system_prompt sets instructions for the whole chat and max_tokens caps the answer. Set private_mode to true to keep the prompt and the answer out of FlyMyAI storage and logs (synchronous calls only).

Call it with a FlyMyAI key in three ways: the FlyMyAI API, the OpenAI-compatible Chat Completions endpoint, or Google's own API under the model's address with the official Google GenAI SDK (generateContent and streamGenerateContent). On the last two your request reaches Google as you send it, so function tools, structured output, prompt caching and streaming work as Google documents them for that API, and FlyMyAI stores neither the prompt nor the answer.

It always thinks. Not offered through FlyMyAI: tools Google runs itself (Google Search and Maps grounding, URL context, code execution), explicit context caches, files in Google's own storage (gs:// and the Files API), model routing and the flex and priority tiers. Billing follows the tokens Google reports for each call: $0.75 input, $0.075 cached input and $3.75 output per 1M tokens. These are Google's introductory prices through 2026-12-31; after that $1.50 input, $0.15 cached input and $7.50 output.

Price: $0.75 per 1M input tokens, $3.75 per 1M output tokens, cached input $0.075 per 1M; from 2027-01-01 $1.50 / $7.50 per 1M.

Run Gemini 3.8 Flash via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

OpenAI-compatible API

Gemini 3.8 Flash also speaks the OpenAI Chat Completions protocol: use the official OpenAI SDK with base URL https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash/openai/v1 and your FlyMy.AI API key.

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash/openai/v1", api_key=os.environ["FLYMYAI_API_KEY"])
response = client.chat.completions.create(
    model="flymyai/gemini-3_8-flash",
    messages=[{"role": "user", "content": "What is a vector database?"}],
)
print(response.choices[0].message.content)

OpenAI-compatible API docs

API documentation · Create a free account · Pricing

Related models