impulse

GLM 4.5 Air

Open weights

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.

API id glm-4.5-airReleased 25 Jul 2025 (Jul 2025)
Input / 1M
$0.20
at Z.ai
Output / 1M
$1.10
at Z.ai
Context window
128K
tokens
Max output
32K
tokens per reply
Hosts
8
8 listings
Released
Jul 2025
25 Jul 2025

Pricing

List prices at Z.ai, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$1.10

What it costs a month

At Z.ai list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$143
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$136
  • Coding agent1,000 requests a day, 40K in / 2K out$306
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$744
Use your own numbers

Where to run it

8 hosts serve GLM 4.5 Air. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Z.aiLab API
glm-4.5-air
$0.20 / $1.10
glm-4.5-air
$0.125 / $0.45
−51% vs headline
Novita AIInference
glm-4.5-air
$0.13 / $0.85
−27% vs headline
Fireworks AIInference
glm-4p5-air
$0.22 / $0.88
−9% vs headline
GMI CloudInference
GLM-4.5-Air-FP8
$0.20 / $1.10
Together AIInference
GLM-4.5-Air-FP8
$0.20 / $1.10
glm-4.5-air
$0.20 / $1.10
glm-4.5-air
$0.18 / $1.18
+1% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: MIT
Runs in about 265.1 GB of GPU memory

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • Pinstripes
    glm-4.5-air
    $0.125 / $0.45
    51% less
  • Novita AI
    glm-4.5-air
    $0.13 / $0.85
    27% less
  • Fireworks AI
    glm-4p5-air
    $0.22 / $0.88
    9% less

Smaller Zhipu AI models

  • GLM 4 32B 128K
    Zhipu AI · on Z.ai
    $0.10 / $0.10
    Has every key capability
    76% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    53% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    53% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    38% less

Open-weight picks

  • MiniMax M3
    MiniMax · on EmpirioLabs AI
    $0.225 / $0.90
    Has every key capability
    7% less
  • Qwen3.5 397B A17B
    Alibaba Qwen · on AIHubMix
    $0.164 / $0.986
    Has every key capability
    13% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    18% less
  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    38% less

Call it

Using Z.ai's API.

Python
from litellm import completion

response = completion(
    model="zai/glm-4.5-air",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 4.5 Air cost?

On Z.ai, GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens. The cheapest host is Pinstripes, at $0.125 per million input tokens and $0.45 per million output tokens.

Which APIs offer GLM 4.5 Air?

GLM 4.5 Air runs on 8 APIs: Z.ai, Pinstripes, Novita AI, Fireworks AI, GMI Cloud, Together AI, Vercel AI Gateway and Kyma API.

What is GLM 4.5 Air's context window?

128K tokens, with up to 32K tokens in one reply.

Is GLM 4.5 Air being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to GLM 4.5 Air?

Models that cost less and keep most of what it can do: GLM 4 32B 128K on Z.ai (76% less), Claude Haiku 5.5 on Anthropic (53% less), GPT-6 Luna on OpenAI (53% less) and MiniMax M3 on EmpirioLabs AI (7% less). GLM 4.5 Air itself costs 51% less on Pinstripes. Savings are on a mix of 3 input tokens to 1 output token.

When was GLM 4.5 Air released?

Zhipu AI released it on 25 Jul 2025.

What is GLM 4.5 Air's API model id?

Use glm-4.5-air with Z.ai. Other hosts use their own ids: glm-4p5-air on Fireworks AI, GLM-4.5-Air-FP8 on GMI Cloud, GLM-4.5-Air-FP8 on Together AI.

Sources

Raw catalog entry for glm-4.5-air on Z.ai
{
  "input_cost_per_token": 2e-7,
  "output_cost_per_token": 0.0000011,
  "litellm_provider": "zai",
  "max_input_tokens": 128000,
  "max_output_tokens": 32000,
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "source": "https://docs.z.ai/guides/overview/pricing"
}