Z.ai · mit

GLM-4.5-Air

Available

GLM-4.5-Air is an open-weight, MoE-based foundation model built for agentic applications (106B total / 12B active parameters). Its hybrid thinking mode combines complex reasoning and tool use with low-latency general chat in a single model.

CHAT REASONING AGENT CODING FP8

Get started → Open in console

Context window

64K

65,536 tokens

Input price

$0.99 / 1M tokens

Output price

$3.49 / 1M tokens

Quickstart

OpenAI-compatible API. Point base_url at the gateway and pass the Model ID in the model field.

Create API key

curl https://llm.fixcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $FXC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.5-air",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")

response = client.chat.completions.create(
    model="glm-4.5-air",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });

const response = await client.chat.completions.create({
  model: 'glm-4.5-air',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);

curl https://llm.fixcloud.ai/v1/chat/completions -N \
  -H "Authorization: Bearer $FXC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.5-air",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")

stream = client.chat.completions.create(
    model="glm-4.5-air",
    messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });

const stream = await client.chat.completions.create({
  model: 'glm-4.5-air',
  messages: [{ role: 'user', content: 'Write a haiku about GPUs.' }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

curl https://llm.fixcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $FXC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.5-air",
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city",
        "parameters": {
          "type": "object",
          "properties": {"city": {"type": "string"}},
          "required": ["city"]
        }
      }
    }],
    "tool_choice": "auto",
    "messages": [{"role": "user", "content": "What is the weather in Istanbul?"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]

response = client.chat.completions.create(
    model="glm-4.5-air",
    messages=[{"role": "user", "content": "What is the weather in Istanbul?"}],
    tools=tools,
    tool_choice="auto",
)
print(response.choices[0].message.tool_calls)

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });

const tools = [{
  type: 'function',
  function: {
    name: 'get_weather',
    description: 'Get the current weather for a city',
    parameters: {
      type: 'object',
      properties: { city: { type: 'string' } },
      required: ['city'],
    },
  },
}];

const response = await client.chat.completions.create({
  model: 'glm-4.5-air',
  messages: [{ role: 'user', content: 'What is the weather in Istanbul?' }],
  tools,
  tool_choice: 'auto',
});
console.log(response.choices[0].message.tool_calls);

curl https://llm.fixcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $FXC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.5-air",
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "city_info",
        "schema": {
          "type": "object",
          "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
          "required": ["city", "country"]
        }
      }
    },
    "messages": [{"role": "user", "content": "Where is the Bosphorus?"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")

response = client.chat.completions.create(
    model="glm-4.5-air",
    messages=[{"role": "user", "content": "Where is the Bosphorus?"}],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "city_info",
            "schema": {
                "type": "object",
                "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
                "required": ["city", "country"],
            },
        },
    },
)
print(response.choices[0].message.content)  # valid JSON

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });

const response = await client.chat.completions.create({
  model: 'glm-4.5-air',
  messages: [{ role: 'user', content: 'Where is the Bosphorus?' }],
  response_format: {
    type: 'json_schema',
    json_schema: {
      name: 'city_info',
      schema: {
        type: 'object',
        properties: { city: { type: 'string' }, country: { type: 'string' } },
        required: ['city', 'country'],
      },
    },
  },
});
console.log(JSON.parse(response.choices[0].message.content));

Capabilities

The features this model offers through the API.

ChatMulti-turn chat via /v1/chat/completions.
ReasoningThinks before answering; returned in the reasoning field.
Agentic workflowsSuited to multi-step agent workflows.
CodingOptimized for code generation, explanation and repair.
Tool callingCalls the tools you define in the OpenAI tools format.
Function callingSupports function-calling schemas.
JSON schemaOutput constrained to a JSON schema via response_format.
Structured outputProduces structured, machine-parseable output.
Prefix cachingRepeated prompt prefixes are served from cache, faster and cheaper.
StreamingToken-level streaming (stream: true).
Batch inferenceAsynchronous bulk jobs (Batch API).

Pricing

Prices are per 1 million tokens. Once the monthly token quota of your plan is used up, usage is billed at these prices.

Input price

$0.99/ 1M tokens

Output price

$3.49/ 1M tokens

Cost estimator

Requests / day

Avg. input tokens

Avg. output tokens

Per request: —
Per day: —
Per month (30 days): —

Enter your expected usage; actual billing follows the token counts measured by the gateway.

View plans

Specifications

Transparency details about the infrastructure serving this model.

Family: glm
Publisher: Z.ai
License: mit
Model ID: glm-4.5-air
Context (tokens): 65,536
Quantization: None (native)
GPUs per replica: 2 × GPU

The model supports a 128K context; it is served with a 64K-token window.

Quickstart

Capabilities

Pricing

Specifications

Request an Enterprise GPU Demo