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.

How to Use Veo 2: Shutdown Status and API Migration

You can no longer generate videos with Veo 2 through Google’s Gemini API or its Google Cloud Agent Platform endpoint. The supplied Google AI Studio documentation excerpt reports that veo-2.0-generate-001 was shut down on June 30, 2026. For a current Google Cloud production route, Google lists Veo 3.1 model veo-3.1-generate-001 as generally available in us-central1 in the United States. (Google AI Studio; Google Cloud Veo 3.1 documentation)

Before you start: Veo 2 is no longer available

The shutdown date has passed, so changing a Veo 2 prompt or API key will not restore that endpoint. Google’s Cloud documentation identifies Veo 3.1 as a current video-generation option on Gemini Enterprise Agent Platform. The Gemini Developer API and the Cloud Agent Platform are separate routes; this guide’s setup below is for the Cloud Agent Platform, not a Gemini API key workflow. (Google AI Studio; Google Cloud text-to-video guide)

Set up the Google Cloud route

Choose or create a Google Cloud project and enable billing. Google’s setup guidance lists a project, billing, and the Agent Platform API as prerequisites. Enabling the API requires the serviceusage.services.enable permission; if you lack it, ask a project administrator to enable the API or grant the required access. (Google Cloud authentication setup; text-to-video guide)
Install the Google Cloud CLI and configure local credentials. In a local shell, sign in and create Application Default Credentials (ADC) for client libraries:
```
gcloud init
gcloud auth application-default login
```
Google distinguishes ADC, which client libraries use, from credentials used by the gcloud CLI itself. (Google Cloud local ADC instructions)
Install the Google Gen AI Python SDK and initialize an Agent Platform client. The SDK documents this client form for Agent Platform; use your project ID and a supported location such as us-central1:
```
pip install --upgrade google-genai
```
```
from google import genai

client = genai.Client(
    enterprise=True,
    project="YOUR_PROJECT_ID",
    location="us-central1",
)
```
This creates the client; it does not generate a video. The SDK supports both the Gemini Developer API and Agent Platform, so keep the enterprise=True Cloud configuration for this route and do not substitute a Gemini API-key client. (Google Gen AI SDK documentation)

Generate and retrieve a video

Google documents Veo 3.1 on Agent Platform for text-to-video generation, and its official Veo 3.1 notebook includes a text-to-video section and helper code for displaying video output. (Google Cloud text-to-video guide; Google’s Veo 3.1 notebook)

Important limitation: the retrieved documentation excerpts for this guide do not establish the exact current Python request fields, operation-polling code, and output-save steps for this Cloud route. The client setup above is therefore not a complete standalone generation script. For those steps, follow the notebook’s Veo 3.1 text-to-video workflow and confirm that its current model ID and code match your installed SDK version. Do not use Veo 2’s retired model ID or assume settings from older Veo 2 instructions carry over.

For prompt writing, start with a clear subject and describe its action and setting; Google’s prompt guide notes that specificity helps avoid generic outputs. For Veo 3.1 on Agent Platform, Google currently lists 4-, 6-, or 8-second durations and 16:9 or 9:16 aspect ratios; check the model documentation for the exact parameters supported by your chosen interface. (Google Cloud prompt guide; Veo 3.1 model specifications)

Bottom line

There is no working Veo 2 API workflow to follow after its reported June 30, 2026 shutdown. For a Google Cloud video-generation integration, begin with the supported Agent Platform route and its Veo 3.1 documentation. The project, billing, API, and local ADC setup are shown above; the linked official notebook supplies the current generation walkthrough, since the retrieved material here was not sufficient to reproduce and verify every request and video-retrieval step inline.

Sources

Veo 2.0 — Google AI Studio Documentation

Veo 3.1 — Gemini Enterprise Agent Platform

Generate videos from text prompts — Gemini Enterprise Agent Platform

Configure application default credentials — Gemini Enterprise Agent Platform

Set up ADC for a local development environment — Google Cloud

Google Gen AI SDK documentation

Veo 3.1 Video Generation — Google Cloud notebook

Video generation prompt guide — Gemini Enterprise Agent Platform