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 2.5 Pro Model Name: Model String and API Status

The short answer

The display name is Gemini 2.5 Pro; its model string is gemini-2.5-pro. Google announced that string for the stable model in June 2025. As of November 12, 2026, Google’s current Gemini API documentation says access is limited to existing users who have actively used the model; it is no longer selectable in Google AI Studio. (aistudio.google.com)

Which identifier should I use in production?

It depends on the API channel:

Google’s Gemini API: For an existing, eligible integration, the documented identifier is gemini-2.5-pro. Google’s dedicated model page says API access is limited to existing users through December 1, 2026, and that requests using this identifier will automatically route to gemini-3.8-flash starting that date. (aistudio.google.com)
Clarifying Google’s status notices: The general deprecations page has a section specifically titled “Gemini 2.5 Pro models” and includes gemini-2.5-pro in its table. It says access is limited to prior users and that these models are “not deprecated” and will continue to be served through the API until further notice. The dedicated model page, by contrast, calls Pro deprecated and gives the December 1 routing date. So the official pages use conflicting deprecation labels, but both describe restricted API access; the dedicated page provides the specific routing date. (ai.google.dev)
Google Cloud’s Gemini Enterprise Agent Platform or a third-party gateway: Don’t assume the Gemini API guidance or identifier applies. Check the model ID and lifecycle information for that specific service. Eden AI, for example, uses its own catalog and endpoint IDs; those are gateway identifiers, not confirmation of Google API access. (docs.cloud.google.com)

For a production integration, confirm that your project remains eligible and check the current notice for the exact API channel before relying on gemini-2.5-pro. Google’s documented December 1, 2026 routing change means the string will no longer identify Pro after that date. (aistudio.google.com)

When might Gemini 2.5 Pro fit?

In its June 2025 announcement, Google positioned Pro for tasks needing high intelligence and broad capabilities, such as coding and agentic work. That is qualitative, dated guidance—not a current benchmark or a claim that Pro is best for every workload. Evaluate the model available through your chosen channel against representative tasks, and check that channel’s current access and limits before selecting it.

Sources

Gemini 2.5 Pro — Gemini API | Google AI Studio

Gemini deprecations | Gemini API | Google AI for Developers

Gemini 2.5: Updates to our family of thinking models

Gemini 2.5 Pro — Gemini Enterprise Agent Platform

Gemini 2.5 Pro API: Pricing, Providers & Performance | Eden AI