Requesty
Sign in

identity

open weights
DeepInfra Inc. logo

zai-org/GLM-4.5-AirDeepInfra Inc.

in /1M$0.20input tokens
out /1M$1.10output tokens
context131K4K out
trainingnoon your prompts
api
chat
hosting
US
model lab
Z.AI
weights
open
added
July 2025
model id
deepinfra/zai-org/GLM-4.5-Air

capabilities 2/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

pricing

no markup
input
$0.20
output
$1.10
cache write
-
cache read
-

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.0310
1M in + 100K out$0.31
10M in + 1M out$3.10

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12

no measured traffic for this endpoint yet. pricing above is the provider's own

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
MMLU Pro81.5
Math Index80.7
AIME 202580.7
GPQA Diamond73.3
LiveCodeBench68.4
τ²-Bench46.5
Terminal-Bench Hard20.5
Intelligence Index11.1
Humanity's Last Exam7.0
9 evalsmean52.2

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-07-28.

policy

data terms
retention
none
trains on prompts
no
hosted in
US

Terms are the provider's, not Requesty's: routing a request here puts it under them. DeepInfra Privacy Policy

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
deepinfra/zai-org/GLM-4.5-Air

this id pins the deepinfra inc. deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="deepinfra/zai-org/GLM-4.5-Air",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.

questions 6

How much does zai-org/GLM-4.5-Air cost?
zai-org/GLM-4.5-Air is priced at $0.20 per million input tokens and $1.10 per million output tokens when accessed via Requesty. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of zai-org/GLM-4.5-Air?
zai-org/GLM-4.5-Air has a context window of 131K tokens, with a maximum output of 4K tokens per response. That is roughly 175 words of input you can fit in a single prompt.
How does zai-org/GLM-4.5-Air perform on benchmarks?
zai-org/GLM-4.5-Air scores 81.5% on MMLU Pro, 80.7% on Math Index, 80.7% on AIME 2025. The benchmarks pane shows every published result, each normalised to 100.
What can zai-org/GLM-4.5-Air do?
zai-org/GLM-4.5-Air supports tool calling, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use zai-org/GLM-4.5-Air with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "deepinfra/zai-org/GLM-4.5-Air". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run zai-org/GLM-4.5-Air through Requesty?
Yes. zai-org/GLM-4.5-Air runs through Requesty's OpenAI-compatible API, served from DeepInfra Inc.. You do not host the model yourself: point base_url at Requesty, set the model to "deepinfra/zai-org/GLM-4.5-Air", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from deepinfra inc. 8

Other DeepInfra Inc. endpoints
endpointctxin /M
glm-5.3-flash1.0M$0.15
glm-5.31.0M$1.20
deepseek-v4-pro-08131.0M$1.30
qwen3.8262K$2.00
deepseek-v4-flash-07311.0M$0.09
deepseek-v4-flash-0731:flex1.0M$0.07
glm-5.2:flex1M$0.60
glm-5.2262K$0.75

call zai-org/glm-4.5-air through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

zai-org/GLM-4.5-Airdeepinfra inc.in $0.20 /1Mout $1.10 /1Mctx 131Khosted US