Poe API
Gemini-3.8-Flash
Google’s fast, cost-efficient workhorse model for coding and agents. Gemini 3.8 Flash delivers strong reasoning at Flash speed, with a 1M-token context window, web search, and adjustable thinking levels.
Powered by a server managed by @google. Learn more
Build with Gemini-3.8-Flash using the Poe API
Start by creating an API key, for use with any bot on Poe:
Use it in these bots
See allCode samples
Responses API
import openai
client = openai.OpenAI(
api_key = "YOUR_POE_API_KEY", # or os.getenv("POE_API_KEY")
base_url = "https://api.poe.com/v1",
)
response = client.responses.create(
model = "gemini-3.8-flash",
input = "Hello world"
)
print(response.output_text)See the full documentation for comprehensive guidance on getting started.
More from Google
New
Gemini-3.8-Flash
Gemini-Omni-1.1-Flash
Gemini-3.7-Flash
Gemini-3.6-Flash
Gemini-3.5-Flash-Lite
Gemini-Omni-Flash
Nano-Banana-2-Lite
Gemini-3.5-Flash
Gemma-4-31B
Veo-3.1-Lite







