LiteLLMModels

GLM 4.5 Air API Pricing

As of October 10, 2026, GLM 4.5 Air costs $0.20 per 1M input tokens and $1.10 per 1M output tokens on Z.ai. Across 6 providers on LiteLLM, the input price ranges from $0.125 to $0.22. It has a 128,000-token context window and returns up to 32,000 tokens per response.

By Z.aiModel ID zai/glm-4.5-airPrices updated Checked
Input
$0.20 / 1M tokens
Output
$1.10 / 1M tokens
Context window
128,000 tokens
Max output
32,000 tokens
Providers
6
Added to LiteLLM
July 2025

GLM 4.5 Air pricing by provider

6 listings across 6 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Z.aizai/glm-4.5-air$0.20$1.10–128K
Fireworks AIfireworks_ai/accounts/fireworks/models/glm-4p5-air$0.22$0.88–128K
Novita AInovita/zai-org/glm-4.5-air$0.13$0.85$0.025128K
Pinstripespinstripes/ps/glm-4.5-air$0.125$0.45–128K
Vercel AI Gatewayvercel_ai_gateway/zai/glm-4.5-air$0.20$1.10–128K
Together AIfp8together_ai/zai-org/GLM-4.5-Air-FP8$0.20$1.10–128K

What GLM 4.5 Air costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Z.ai$0.95
Pinstripes$0.475
Novita AI$0.685
Vercel AI Gateway$0.95

100 long-document requests with 100,000 input and 2,000 output tokens each

Z.ai$2.22
Pinstripes$1.34
Novita AI$1.47
Vercel AI Gateway$2.22

GLM 4.5 Air features

Use GLM 4.5 Air with LiteLLM

Call GLM 4.5 Air through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="zai/glm-4.5-air",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: glm-4.5-air
    litellm_params:
      model: zai/glm-4.5-air
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "glm-4.5-air",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GLM 4.5 Air FAQ

How much does GLM 4.5 Air cost?

GLM 4.5 Air costs $0.20 per 1M input tokens and $1.10 per 1M output tokens on Z.ai. Across 6 providers on LiteLLM, the input price ranges from $0.125 to $0.22.

What is the context window of GLM 4.5 Air?

GLM 4.5 Air has a 128,000-token context window and returns up to 32,000 tokens per response.

Which providers offer GLM 4.5 Air?

GLM 4.5 Air is available from 6 providers through LiteLLM: Z.ai, Fireworks AI, Novita AI, Pinstripes, Vercel AI Gateway and Together AI. The lowest price is on Pinstripes.

How do I call GLM 4.5 Air with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="zai/glm-4.5-air", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does GLM 4.5 Air support?

GLM 4.5 Air supports function calling, parallel tool calls, structured output, reasoning and prompt caching.

When did LiteLLM add GLM 4.5 Air?

GLM 4.5 Air was added to LiteLLM's model price file in July 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Z.ai, Fireworks AI, Pinstripes, Vercel AI Gateway, Together AI.

Provider pages: Z.ai, Fireworks AI, Novita AI, Pinstripes, Vercel AI Gateway, Together AI.