glm-4.5-air

ChatGLM · Chat

ConversationThinking

NixAPI price, from

Input$0.1014
Output$0.5577

USD per 1M tokens · via group Self-Deployed-1 · Official list price $0.2 / $1.1Save 49%

Get your API key →

About glm-4.5-air

GLM-4.5 and GLM-4.5-Air are the latest flagship model series, built as foundation models for Agent applications. Both use a Mixture-of-Experts (MoE) architecture. GLM-4.5 has 355B total parameters with 32B active; GLM-4.5-Air uses a leaner design with 106B total parameters and 12B active.

Price by routing group

Pick a group in the console when you create a key. Status is live from the router. Live status by group →

GroupGroup statusModel statusMultiplierInputOutputCache readCache write
Self-Deployed-1…×0.507$0.1014$0.5577$0.0152—
Alibaba-1…×0.845$0.169$0.9295$0.0254—
Self-Deployed-2…×0.845$0.169$0.9295$0.0254—
Alibaba-2…×1.2675$0.2535$1.394$0.038—
Alibaba-3…×1.859$0.3718$2.045$0.0558—

USD per 1M tokens

Long-context pricing

  • Prompts over 32,000 tokens: input ×1.5, output ×1.33334

Supported endpoints

openai

Call glm-4.5-air in one request

Works with the OpenAI SDK and any OpenAI-compatible client. Replace the key with your own.

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

Full API reference →

Questions about glm-4.5-air

How much does glm-4.5-air cost on NixAPI?

From $0.1014 per 1M input tokens and $0.5577 per 1M output tokens in the Self-Deployed-1 group, about 49% below the official list price. Prices are pay-as-you-go in USD with no monthly minimum.

How do I call glm-4.5-air?

Point any OpenAI-compatible client at https://api.nixapi.com/v1, use your NixAPI key and set the model to "glm-4.5-air".

Which routing groups serve glm-4.5-air?

glm-4.5-air is available in 5 routing groups: Self-Deployed-1, Alibaba-1, Self-Deployed-2, Alibaba-2, Alibaba-3. The lowest price is in Self-Deployed-1.

More from ChatGLM

Compare all ChatGLM models →