Z.AI

Use Z.AI with Blazen — construct the ZaiProvider and call complete().

Z.AI is an OpenAI-compatible LLM provider. Construct it like any other Blazen provider — build a list of ChatMessages, call complete() (or stream()), and read back a typed ModelResponse.

Z.AI GLM Coding Plan OpenAI-compatible endpoint; chat at {base}/chat/completions with Bearer auth. GLM coding/reasoning completions run long and stream reasoning_content, so the streaming-safe HTTP client is used.

At a glance

Provider id	zai
Base URL	https://api.z.ai/api/coding/paas/v4
Default model	glm-4.6
API key env var	ZAI_API_KEY
Auth	Authorization: Bearer <key>

Set ZAI_API_KEY in the environment and Blazen reads it automatically, or pass the key explicitly when you construct the provider.

Capabilities

Capability	Supported
Streaming	Yes
Tool calling	Yes
Structured output	Yes
Vision	No
Model listing	No
Embeddings	No

Usage

Construct the provider and call complete(). The default model is glm-4.6; override it with with_model / model when you need a different one.

use blazen_llm::{Model, ModelRequest, ChatMessage};
use blazen_provider_zai::ZaiProvider;

// Reads ZAI_API_KEY from the environment, or pass the key to `new`.
let model = ZaiProvider::new(std::env::var("ZAI_API_KEY")?);

let resp = model
    .complete(ModelRequest::new(vec![ChatMessage::user("Hello")]))
    .await?;
println!("{}", resp.content.unwrap_or_default());

from blazen import ZaiProvider, ProviderOptions, ChatMessage

# Omit the api_key to read ZAI_API_KEY from the environment.
model = ZaiProvider(options=ProviderOptions(api_key="..."))

resp = await model.complete([ChatMessage.user("Hello")])
print(resp.content)

import { ZaiProvider, ChatMessage } from "blazen";

// Omit apiKey to read ZAI_API_KEY from the environment.
const model = ZaiProvider.create({ apiKey: "..." });

const resp = await model.complete([ChatMessage.user("Hello")]);
console.log(resp.content);

Streaming

async for chunk in model.stream([ChatMessage.user("Count to five")]):
    print(chunk.delta, end="")

await model.stream([ChatMessage.user("Count to five")], (chunk) => {
  if (chunk.delta) process.stdout.write(chunk.delta);
});

See also

• Models & Providers — the canonical provider + ModelManager guide