Gemini 3.1 Pro

Frontier

Google GeminiReasoninggemini-3.1-pro-preview

Google’s top model — strongest multimodal + long-document reasoning. Google designates this tier "Preview".

Google designates this Preview — it is their current top Pro tier (the prior gemini-3-pro-preview was shut down 2026-03). Google bills prompts >200k tokens at a higher tier; Conduix's flat rate is based on the ≤200k tier.

Capabilities

Tool callingVisionReasoningJSON mode

Recommended for

multimodal reasoning
long-document work
video understanding

Using this model through Conduix

Call it by its id, or let a routing alias pick it as part of a governed, cross-provider chain with automatic failover.

Direct model idgemini-3.1-pro-preview

Reached by these routing aliases:

frontier-bestfallback #2 · GPT-5.5 → Claude Opus 4.8 → Gemini 3.1 Pro
vision-bestprimary pick · Gemini 3.1 Pro → GPT-5.5 → Claude Opus 4.8
document-aiprimary pick · Gemini 3.1 Pro → Gemini 3.5 Flash → Claude Sonnet 5

Routing relationships are operational — chains adapt to provider availability and your org's policy — not a contractual guarantee that a specific model serves a given request.

Get started

Conduix is OpenAI-API-compatible — point any OpenAI SDK at https://api.conduix.ai/v1 and pass gemini-3.1-pro-preview as the model.

from conduix import Conduix

client = Conduix(api_key="cx_live_YOUR_KEY")  # base URL is built in

response = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user", "content": "Hello, Conduix!"}],
)
print(response.choices[0].message.content)

Tool calling: Pass a tools array and the model calls your functions.
Vision: Accepts image inputs — add image_url parts to a message.
Reasoning: Reasons step-by-step — best for hard, multi-step problems.
JSON mode: Set response_format for guaranteed-valid JSON output.

The response's x-conduix-model-served header tells you exactly which model answered. See the quickstart for keys, headers, and usage.