GLM 4.5 Air

z-ai/glm-4.5-air
ToolsJSONReasoning
by Z.ai · 2025-07-25

Compact MoE sibling of GLM-4.5: 106B total / 12B active. Same hybrid-reasoning and tool-calling stack tuned for high-throughput, low-cost inference. 128K context.

ctx128K tokens
Max output96K
Inputtext
Outputtext
p50 TTFT1.88 s
INPUT$0.20/ 1M tokens
OUTPUT$1.10/ 1M tokens
p50 TTFT1.88 s7d
p95 TTFT10.00 s7d
TRAFFIC534.7Ktokens / 7d

GLM 4.5 Air is a text-generation language model developed by Z.ai. It offers a context window of 128,000 tokens and can generate up to 96,000 tokens in a single response. The model is optimized for…

What is GLM 4.5 Air?

Who should use GLM 4.5 Air?

What modalities does GLM 4.5 Air support?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

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

Supported parameters

  • do_sample
  • include_reasoning
  • max_tokens
  • reasoning
  • request_id
  • response_format
  • stop
  • stream
  • temperature
  • thinking
  • tool_choice
  • tool_stream
  • tools
  • top_p
  • user_id

Pricing

Input / 1M tokens$0.200
Output / 1M tokens$1.10
Cache read / 1M$0.030
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $4.70 · With prompt caching $4.11

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000554

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.88 s
Output speed
90.2 tok/s
p95 TTFT
10.00 s
Error rate
7.1%

Public benchmarks

23.8
AA Coding
Better than 25% of models compared
#79 of 106
23.2
AA Intelligence
Better than 21% of models compared
#87 of 110
80.7
AA Math
Better than 70% of models compared
#23 of 81
AIME
67.3
AIME 2025
80.7
GPQA Diamond
73.3
Humanity's Last Exam
6.8
IFBench
37.6
LiveCodeBench
68.4
Long-Context Recall
43.7
MATH-500
96.5
MMLU-Pro
81.5
SciCode
30.6
TerminalBench Hard
20.5
τ²-Bench
46.5
Source: artificialanalysis.ai

How it compares

GLM 4.5 AirGLM 5.1GLM 5.2GLM 5
Input $/M$0.20$1.40$1.40$1.00
Output $/M$1.10$4.40$4.40$3.20
Context128K200K1.0M200K
Quality6/109/109/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use GLM 4.5 Air on OrcaRouter?
The cost is $0.20 per 1 million input tokens and $1.10 per 1 million output tokens. This is billed at the provider rate with zero markup on OrcaRouter. No additional platform fees apply.
What is the context window size of GLM 4.5 Air?
The context window is 128,000 tokens. The maximum output is 96,000 tokens per response. Both input and output tokens count toward the total context limit.
What are the main strengths of GLM 4.5 Air?
It achieves a score of 96.5 on the MATH-500 benchmark, indicating strong mathematical reasoning. It also offers a large context window and high output limit, making it suitable for long-form generation and document processing.
How does GLM 4.5 Air compare to other GLM-4 models?
GLM 4.5 Air is an optimized variant of the GLM-4 series. Specific differences in performance or speed are not provided, but the "Air" designation typically implies a balance of efficiency and capability. Refer to OrcaRouter’s catalog for other GLM-4 model details.
Does GLM 4.5 Air support image or audio inputs?
No. It is a text-only model. It accepts only text input and generates text output. It cannot process images, audio, or video.
How do I call GLM 4.5 Air via the OrcaRouter API?
Send requests to https://api.orcarouter.ai/v1 with the model ID "z-ai/glm-4.5-air". Use a standard OpenAI-compatible chat completion format with your API key. Supported parameters include temperature, max_tokens, top_p, stop, and streaming.
Is GLM 4.5 Air suitable for real-time applications?
Latency depends on input/output length and server load. While it can generate short responses quickly, generating the maximum 96,000 tokens will take longer. Test under expected load to determine if speed meets your requirements.
What data handling policies apply when using GLM 4.5 Air through OrcaRouter?
Data handling is governed by OrcaRouter’s privacy policy and terms of service. As a hosted API, data may be processed on third-party servers. Z.ai and OrcaRouter may have specific data retention practices. Review the platform’s data processing agreement for details.
Can I use GLM 4.5 Air for free?
OrcaRouter likely requires a paid subscription or pay-as-you-go credits. There is no free tier mentioned. Check OrcaRouter’s pricing page for any trial credits or promotional offers.
How do I migrate from OpenAI’s API to GLM 4.5 Air on OrcaRouter?
Change your base URL to https://api.orcarouter.ai/v1, set the model to "z-ai/glm-4.5-air", and use your OrcaRouter API key. The request and response format is identical to OpenAI’s chat completions, so minimal code changes are needed.

Embed this badge

Z.ai: GLM 4.5 Air$0.20/M in1875ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/z-ai/glm-4.5-air" target="_blank"> <img src="https://www.orcarouter.ai/embed/z-ai/glm-4.5-air.svg" alt="Z.ai: GLM 4.5 Air on OrcaRouter" /> </a>
Markdown [![Z.ai: GLM 4.5 Air](https://www.orcarouter.ai/embed/z-ai/glm-4.5-air.svg)](https://www.orcarouter.ai/models/z-ai/glm-4.5-air)

Model card as data

GET /api/public/models/z-ai/glm-4.5-airOpen
Machine-readable:/llms.txt/llms-full.txt