Z.ai

@ai-sdk/zai is the official Provider in the Vercel AI SDK for Zhipu AI models.

@ai-sdk/zai depends on @ai-sdk/openai-compatible, indicating that Zhipu GLM's API interface is largely compatible with OpenAI's calling conventions.

@ai-sdk/zai, as the Provider implementation for Z.ai, reuses the communication and protocol handling logic of the OpenAI compatibility layer at its foundation.

The API service brand offered externally by Zhipu AI is Z.ai (formerly the BigModel open platform).

GLM-5.3-Flash, from Z.ai, is a multimodal MoE model with a total of 320B (320 billion) parameters, with only 18B parameters activated at any given time.

The models tested include Google's Gemini 3.7 Flash, Z.ai's GLM-5, Alibaba's Qwen 3 235B A22B Instruct, and OpenAI's gpt-oss-120b, all running on Kaggle.

Z.ai 适配器沿用 AI SDK 整体的语义化版本节奏：补丁号递增对应依赖刷新与内部修复，次版本号对应新能力接入。

Kimi K3 is provided by Moonshot AI, GLM 5.3 is provided by Z.ai, and DeepSeek V4.1 Flash is provided by DeepSeek.ai.

GLM-5.3-Flash is a multimodal MoE model with 320B total parameters and 18B activated per token, under the MIT license, supporting a 1M token context.

Z.ai claims that GLM-5.3-Flash is close to Claude Opus 4.8 on coding and agent benchmarks and costs one tenth of GLM-5.2's price.

GLM (glm-4.5-air) is Zhipu AI's large language model series, called via the OpenAI-compatible API provided by Z.ai, with interface paths, request bodies, and response formats largely consistent with the OpenAI Chat Completions specification.

IboChat's endpoint name is still /api/gemini because early versions used Google Gemini, and it now proxies to Z.ai; changing the name would break the frontend.

IboChat's tech stack includes a single-file Flask application, GLM glm-4.5-air via the Z.ai API, locally running faster-whisper, SQLite + Werkzeug hashed account management, and Docker deployment behind Cloudflare.

Z.ai's GLM Coding Plan starts at $18/month, with the Lite tier at 2,000 credits per 5 hours, the Pro tier at 12,000, and the Max tier at 28,000, supporting GLM-5.3 and GLM-5.3-Flash.

In 2026, Kimi, Z.ai (GLM), and Alibaba Cloud Qwen all launched monthly coding plans for developers, with the core logic being to limit usage by 5-hour windows rather than billing by token.

Z.ai's choice to integrate through openai-compatible is an efficiency-first strategy, with the cost being that when Z.ai has unique capabilities beyond the OpenAI specification, the compatibility layer may need additional adaptation code.

DeepSeek's models handled 58% of all gateway tokens but accounted for only 6.6% of spend; Moonshot AI took 3.6% of tokens and 13.2% of spend; Z.ai took 7.2% of tokens and 4.5% of spend.

Typical representatives of open-weight models include Meta's Llama series, the DeepSeek series, Moonshot's Kimi, Z.ai's GLM, and others; companies such as Mistral and Cohere adopt a hybrid model of open weights plus commercial services.

GLM 5.3 comes from Z.ai (the overseas brand of Zhipu AI), and Kimi K3 comes from Moonshot AI; both are domestic Chinese models that perform outstandingly on code generation and reasoning tasks.

AppBlips uses a BYOK (Bring Your Own Key) model, supports connecting to OpenAI, OpenRouter (which can access Claude, Gemini, etc.), DeepSeek, Z.ai, local Ollama models, or any service compatible with the OpenAI interface, and does not charge credit markups.