canonical: https://jentic.com/apis/open.bigmodel.cn/open-bigmodel

# Open Bigmodel Cn Zhipu AI GLM API

The Zhipu AI GLM API provides access to Zhipu's GLM family of large language models through an OpenAI-compatible interface. It creates chat completions, text embeddings, image generations, and video generations, polls long-running generation tasks by task id, manages uploaded files, and runs batch processing jobs. Developers use it to add GLM-powered reasoning, multimodal generation, and bulk inference to their applications.

## For AI agents

Create chat completions, embeddings, and image and video generations with Zhipu's GLM models, poll async tasks, manage files, and run batch inference jobs via an OpenAI-compatible interface.

## Scope

Does not handle model fine-tuning, vector storage, or speech transcription. Use for GLM text, image, and video generation only.

## Capabilities

- Create chat completions with Zhipu's GLM models
- Generate text embeddings for semantic search and retrieval
- Generate images from a text prompt
- Generate video from text or an image prompt
- Poll a long-running generation task by its task id
- Upload and manage files and run batch inference jobs

## Use cases

### AI Assistant on GLM

An AI agent connected through Jentic answers and reasons using Zhipu's GLM models by calling the chat completion operation, so a product can run on GLM without the developer wiring the Zhipu auth and request format by hand. The OpenAI-compatible shape means prompts and tool calls map across with minimal change.

Example prompt: Send a multi-turn conversation to a GLM chat model and return the assistant's reply

### Multimodal Generation

A content tool generates visuals by sending a text prompt to the image generation operation and a text or image prompt to the video generation operation, polling each long task by its task id until the asset is ready. One provider covers text, image, and video output.

Example prompt: Generate an image from a prompt, then poll the task id until the image URL is returned

### Batch Inference

A data pipeline runs large sets of prompts cost-effectively by uploading an input file and submitting a batch job, then collecting results when the job completes. Files and batches are tracked by id, so a pipeline can fire many jobs and reconcile outputs asynchronously.

Example prompt: Upload a prompt file, create a batch job over it, and retrieve the results once the job completes

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/chat/completions` | Create a chat completion |
| POST | `/embeddings` | Create text embeddings |
| POST | `/images/generations` | Generate images from text |
| POST | `/videos/generations` | Generate video from text or image |
| GET | `/async-result/{task_id}` | Get an async task result |
| POST | `/batches` | Create a batch processing job |
| GET | `/files` | List uploaded files |

## Key resources

- **Chat** — Chat completions with GLM models
- **Embeddings** — Text embedding vectors
- **Generation** — Image and video generation with async task results
- **Files** — Upload, list, read, and delete files
- **Batches** — Batch inference jobs tracked by id

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 66 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 87 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 49 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 71 / 100
- **View full report:** https://jentic.com/apis/open.bigmodel.cn/open-bigmodel/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the Zhipu GLM API by hand means handling its bearer token, polling async generation tasks, and tracking file and batch job state yourself. Through Jentic you install once, import Zhipu GLM from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** A rule can give your agent just the chat and embedding operations and leave file deletion, image, video, or batch operations out unless you add them. You choose which operations it may call.
- **Credential handling:** Your Zhipu GLM API token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'generate a chat completion' or 'create an image', and Jentic returns the matching Zhipu GLM operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **OpenAI API** — Chat, embedding, and image models through a widely used interface.
- **Anthropic Messages API** — Claude models for chat and reasoning via the Messages API.
- **Mistral AI API** — Open-weight and hosted chat and embedding models.
- **Pinecone API** — Managed vector database for storing and querying embeddings.

## FAQ

### What authentication does the Zhipu AI GLM API use?

The Zhipu AI GLM API authenticates with a bearer token in the Authorization header, per its OpenAPI spec, following the OpenAI-compatible convention. Through Jentic that token is held encrypted by your own Jentic One instance and injected at call time, so it never appears in the agent's prompt or logs.

### Can I generate images and video with the Zhipu AI GLM API?

Yes. The image generation operation turns a text prompt into images, and the video generation operation produces video from text or an image. Both can run as long tasks you poll by task id until the output is ready.

### What are the rate limits for the Zhipu AI GLM API?

The OpenAPI spec does not define rate limits for the Zhipu AI GLM API. Zhipu sets per-account limits that vary by model, documented at https://open.bigmodel.cn/dev/api, so check there before scaling up.

### Can I limit what my agent is allowed to do with the Zhipu AI GLM API?

Yes. Write a rule that allows only the chat and embedding operations, so the agent reasons and embeds while file deletion, image, video, and batch operations stay out of its reach unless you add them. Every call the agent makes is logged.

### How do I create a chat completion with the Zhipu AI GLM API through Jentic?

Search by intent in Jentic with a query like 'generate a GLM chat completion', add the Zhipu AI GLM API from the Jentic API Directory, and your agent sends the conversation to a GLM model and reads the reply. To run it on your own infrastructure, install Jentic One from its GitHub repo.