Internalize
Learn knowledge into model weights. Keep the source out of subsequent prompts.
Internalize turns a passage of knowledge into a versioned adapter for GLM 5.3. Call internalize for a subject, wait for training and validation, then send questions to the same subject. Internalize hosts the adapter and routes new requests to its active version.
The source is used during learning. It is not appended to later inference messages. Your application still sends the question and any instructions or conversation it needs; the learned knowledge is carried by the adapter weights.
Hosted preview
The console is currently open for exploration. Billing is a preview and model execution is disabled. The guides below describe the implemented API contract for enabled projects. See availability before running examples.
Start here
Make your first call
Internalize a policy, wait for activation, and ask without the source.
Understand the system
Subjects, context distillation, validation, and managed weights.
API reference
Every endpoint, request field, response, limit, and error.
Connect an agent
A durable tool call with explicit learning and activation outcomes.
The three operations
| Operation | Your application sends | Internalize returns |
|---|---|---|
| Learn | A subject and a self-contained knowledge passage | A job that can produce a validated adapter candidate |
| Activate | A candidate and the version you expect to replace | A new active version, if the subject has not changed |
| Ask | The same subject and inference messages | A job with the answer, resolved adapter, usage, and charge |
Learning activates automatically by default. Explicit activation is useful for reviewed releases and rollback. In both cases, already-running requests keep the version chosen when they were admitted.
Find the right guide
Use Getting started to prepare a project and credentials. The Product guide explains each console workspace. Concepts covers the model and state boundaries; Guides shows how to structure knowledge, evaluate updates, and deploy them.
For an integration, choose TypeScript, Python over HTTP, or the endpoint reference. For operations, start with billing, job recovery, and safe diagnostics.
Validation is evidence about the checks run for one candidate. It is not a guarantee of perfect recall or general understanding. Test the questions, applications, and failure cases your product depends on before relying on a new version.
Machine-readable documentation
Agents can discover these same guides through /llms.txt, read the complete set at /llms-full.txt, or fetch individual Markdown pages. The OpenAPI specification describes the public HTTP interface. These surfaces share the documentation source used by this site.