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.

Is GLM-5.1 Free? API Pricing, Free Access, and Availability

Short answer: GLM-5.1 weights may be free to use; API calls have published rates

Z.ai lists GLM-5.1 standard API inference at $1.40 per 1 million input tokens and $4.40 per 1 million output tokens. Whether free credits can cover GLM-5.1 API calls depends on eligibility and offer terms; a general free quota for this model is not confirmed by the sources reviewed. The model repository’s MIT license concerns use of the weights, not the cost of hosted inference. (Z.ai pricing; GLM-5.1 model repository)

Z.ai separately advertises a startup program with free API credits of up to 1 billion tokens. Its public description does not establish whether GLM-5.1 standard API calls qualify, or specify the eligibility, expiration, or usage limits for an individual account. Z.ai’s FAQ says platform credits can offset API-call fees, but check the program and your account before treating credits as available for GLM-5.1. (Z.ai Startups Program; Z.ai FAQ)

The pricing page lists cached input at $0.26 per million tokens and says cached-input storage is limited-time free. That storage offer is distinct from free general inference. (Z.ai pricing)

`Z.ai` API budget: estimate by tokens

Z.ai’s pricing table lists these USD rates for GLM-5.1:

Usage type	Published price
Input	$1.40 / 1 million tokens
Cached input	$0.26 / 1 million tokens
Cached-input storage	Limited-time free, per the pricing table
Output	$4.40 / 1 million tokens

For a simple, uncached estimate, calculate input tokens × $1.40 per million, plus output tokens × $4.40 per million. For example, 100,000 input tokens and 20,000 output tokens would cost about $0.23: $0.14 for input plus $0.088 for output. This is an illustrative calculation, not a test; actual billed usage depends on token counts and applicable cache treatment. Z.ai states its listed prices are in USD. (Z.ai pricing)

Older third-party pages report different rates, and API gateways may set their own prices. For a Z.ai API estimate, use Z.ai’s published rate card rather than treating those other figures as Z.ai prices.

Is GLM-5.1 available for production API use?

Z.ai’s pricing table lists GLM-5.1, and its developer documentation describes the model and API capabilities. That supports a documented Z.ai API offering, but documentation alone does not confirm that a particular account can successfully call it right now. Before production deployment, confirm the model ID and access in your Z.ai account and test a small request in your intended environment. (Z.ai pricing; GLM-5.1 documentation)

A retirement notice from Doubleword says GLM-5.1 was retired from Doubleword’s API on October 30, 2026. That notice is provider-specific; it does not establish that GLM-5.1 has been retired from every API service. (Doubleword)

The Coding Plan is separate from standard API billing

Z.ai advertises its Coding Plan starting at $18 per month. It is a subscription for supported coding and agent tools, not the standard per-token API rate. Current plan documentation says requests for GLM-5.1 through the plan are automatically routed to GLM-5.3. The plan FAQ also limits its quota to supported tools; it does not make that quota general-purpose standard API access. (Coding Plan overview; Coding Plan FAQ)

What “free” means for the model weights

The GLM-5.1 Hugging Face repository lists the model under an MIT license. The license text requires including its copyright and permission notices in copies or substantial portions. That concerns the model and license terms—not free compute, hosting, or API service. Running weights yourself can still involve hardware and operating costs. (GLM-5.1 license)

Is the API a fit for production?

Z.ai documents GLM-5.1 as a text model with function calling, streaming, a 200K context window, and up to 128K output tokens. Those features make it a candidate to evaluate for coding agents and other tool-using workflows, but they do not guarantee reliability, latency, or quality for your application. Test representative tasks, measure token usage and failure rates, and set a spending limit before routing production traffic. (GLM-5.1 documentation)

Bottom line: GLM-5.1 weights are listed under an MIT license, while Z.ai publishes paid standard API rates of $1.40 per million input tokens and $4.40 per million output tokens. Z.ai also advertises startup API credits, but the public information reviewed does not confirm that a particular reader qualifies to use them for GLM-5.1 calls. Budget at the published rates unless your account or program terms confirm eligible credits. Verify model access before relying on it in production.