What does Token Forge Cloud do?

Token Forge Cloud provides managed APIs for Qwen, DeepSeek, GLM, and Seedance, with additional video and speech models for teams building production AI products. Proven workloads can also move into a Neo Cloud marketplace product path.

Who is Token Forge Cloud built for?

It is built for product and enterprise teams that need reliable language, reasoning, coding, agent, and video model access without operating every provider stack themselves.

Can teams start with APIs before buying through Neo Cloud?

Yes. Teams can begin with managed API access for Qwen, DeepSeek, GLM, Seedance, and additional media models, then move predictable production traffic into a Neo Cloud marketplace product path.

Which AI workflows does Token Forge Cloud support?

Token Forge Cloud supports assistants, reasoning, coding, agents, text-to-video, image-to-video, asynchronous jobs, model routing, and speech generation.

How does Token Forge Cloud handle security and data control?

Token Forge Cloud supports role policies for who can call which models and workflows, controlled access for prompts and application data, and audit-ready request, generation, and routing telemetry.

Gemini 3 Pro API: Model Status and Python Quickstart

The original gemini-3-pro-preview model was shut down on March 9, 2026. Google’s Gemini API deprecation table lists gemini-3.1-pro-preview as its replacement, while the retired model page now advises migrating to Gemini 4 Argon. Because those Google pages point to different migration targets, check the current model page and deprecation guidance before choosing a replacement. (ai.google.dev)

For a Gemini 3 Pro-series request through the Gemini API, Google’s current model page lists gemini-3.1-pro-preview. It is still labeled Preview and Paid. This quickstart uses the Gemini API and Google AI Studio—not the separate Google Cloud Gemini Enterprise Agent Platform route. (ai.google.dev)

Make a first Gemini 3.1 Pro API request

1. Create a key and prepare the project

Create or manage a Gemini API key in Google AI Studio. Google says new AI Studio keys have defaulted to authorization keys since May 28, 2026. Authorization keys are bound to a Google Cloud service account and restricted to the Generative Language API by default. The Gemini API accepts standard or authorization keys; Google’s SDK migration guide says the Python client reads GEMINI_API_KEY from the environment when no key is passed to the client. Together, those docs support the environment-variable setup below for an AI Studio authorization key. (aistudio.google.com)

The gemini-3.1-pro-preview model page marks this model Paid. Use a project on the Gemini API paid tier for this request; Google describes paid access as including its most advanced models. The key is associated with a project, so make sure it belongs to the project you intend to use. (ai.google.dev)

On macOS or Linux, set the key in your shell (replace the placeholder with your key):

export GEMINI_API_KEY="YOUR_API_KEY"

Keep the key out of browser-side code and source control. For production key-management guidance, follow Google’s API key documentation.

2. Install the Python SDK

Google recommends its Google GenAI SDK for Gemini API integrations. Install or update it with: (ai.google.dev)

python3 -m pip install -U google-genai

The cited SDK documentation does not specify a minimum Python version for this example.

3. Save and run the request

Save this as gemini_pro_quickstart.py:

from google import genai

client = genai.Client()  # Reads GEMINI_API_KEY from the environment

response = client.models.generate_content(
    model="gemini-3.1-pro-preview",
    contents="Explain what an API is in one sentence.",
)

print(response.text)

Run it with:

python3 gemini_pro_quickstart.py

Google documents the genai.Client() and generate_content pattern, and the model page supplies the Pro model ID. Its text-generation example uses a different model, so this snippet combines the documented call pattern with the listed Pro ID; it is not a report of an independently executed test. (ai.google.dev)

Expected result: the script prints a text response. Before running it, confirm that the environment variable is set in the same shell and that the key’s project has paid-tier access to this model. The pages cited here do not specify a separate model-specific IAM role for this Gemini API request.

Gemini API versus Google Cloud

This example uses the Gemini API with an AI Studio key. Google separately documents Gemini on Gemini Enterprise Agent Platform, including its own project, location, and authentication setup. Do not copy that route’s Cloud environment variables into this Gemini API example; use the setup for the API product you have chosen. (docs.cloud.google.com)

What to check before adopting the model

Google’s Gemini API model page lists gemini-3.1-pro-preview as Preview, with text output, a 1,048,576-token input limit, and a 65,536-token output limit. Preview status is not the same as a generally available model designation. Check the current lifecycle and model pages before relying on a model ID for a deployment. (ai.google.dev)

Is `gemini-3-pro-preview` still available?

No. Google’s Gemini API deprecation table says gemini-3-pro-preview shut down on March 9, 2026. Google’s deprecation table and retired-model page currently differ on the named migration target, so verify the target in Google’s current model documentation before changing an integration. (ai.google.dev)

Is `gemini-3.1-pro-preview` free to use?

Google labels the model Paid. Its pricing page describes paid access as the tier for higher-volume production deployments and access to its most advanced models. Check that the key’s project is on the appropriate tier before sending a request. (ai.google.dev)