OpenRouter
Coming soongoogle/gemini-3.1-pro-preview
Frontier · 1M context
Gemini 3.1 Pro Preview. Compare provider offers, token prices, and published task evidence below.
1 connected provider · 2 coming soon
Choose one API ID. Code examples, Playground and Routes use your selection.
Reference offers only. These providers cannot be called through our API yet.
google/gemini-3.1-pro-preview
google/gemini-3.1-pro-preview
gemini-3.1-pro-previewGemini 3.1 Pro Preview. Compare provider offers, token prices, and published task evidence below.
Call this model directly with any OpenAI-compatible SDK. Set base_url to the URL below and pass your API key. Sign up for an API key →
# pip install openai
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.taskrouter.com/v1",
api_key=os.environ["TASKROUTER_API_KEY"],
)
reply = client.chat.completions.create(
model="gemini-3.1-pro-preview",
messages=[{"role": "user", "content": "Hello! How can you help me today?"}],
)
print(reply.choices[0].message.content)https://api.taskrouter.com/v1Header: Authorization: Bearer $TASKROUTER_API_KEYEach task has a minimum pass rate. A model passes the task when its pass rate reaches that minimum.
67.0% pass rate · 80% minimum · 4.98s p50
Below the minimum
11.0% pass rate · 80% minimum · 15.43s p50
Below the minimum
98.0% pass rate · 80% minimum · 4.76s p50
Passes the task
92.0% pass rate · 80% minimum · 6.17s p50
Passes the task
The Playground and task routes choose from all models that pass the task, so they may not use this model.