BroadRouter

GLM 4.5 Air API pricing

Updated

Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for GLM 4.5 Air is Novita AI at USD 0.13 per 1M input tokens and USD 0.85 per 1M output tokens. The median across 4 standard prices is USD 0.17 / USD 0.98. Z.ai's own API charges USD 0.20 / USD 1.10.

Z.ai · slug glm-4.5-air · up to 131,076 tokens of context · 4 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-01-01 (3 archived price points, 0 list-price changes): LLM API price history.

What does Z.ai charge for GLM 4.5 Air?

Input
USD 0.20
Cached input
USD 0.03
Output
USD 1.10
Blended 3:1
USD 0.425

USD per 1M tokens on Z.ai, model GLM-4.5-Air, standard tier. Source, checked 2026-11-14.

Is a host cheaper than Z.ai? Yes. Novita AI charges USD 0.13 input and USD 0.85 output per 1M tokens, 27% below Z.ai's own USD 0.20 / USD 1.10 on the 3:1 blend.

GLM 4.5 Air model facts

Facts from Z.ai's model card for zai-org/GLM-4.5-Air and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

GLM 4.5 Air: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (zai-org/GLM-4.5-Air) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 47 .safetensors files listed”
LicenceMIT (mit)Z.ai model card metadata, checked 2026-11-16
Quote
“license: mit”
Total parameters106BZ.ai model card, checked 2026-11-16
Quote
“GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters”
Active parameters per token12BZ.ai model card, checked 2026-11-16
Quote
“GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters”
Context lengthNot found on Z.ai's model card when we read it; see the context column in the price tablechecked 2026-11-16
Input and outputText in, text out (the card's task tag is text-generation)Z.ai model card metadata, checked 2026-11-16
Quote
“pipeline_tag: text-generation”
Tool callingNot found on Z.ai's model card when we read itchecked 2026-11-16
First published on Hugging Face (not necessarily the release date)2025-07-20Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2025-07-20T03:25:55.000Z"”

GLM 4.5 Air price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 37% above the cheapest.

GLM 4.5 Air API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Novita AI cheapest
zai-org/glm-4.5-air
Notes and source quote
“GLM 4.5 Air 128K $0.13 /Mt · Cache Read $0.025 /Mt $0.85 /Mt”
USD 0.13USD 0.025USD 0.85USD 0.31131,072not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
2SiliconFlow
Notes and source quote

Context shown as 131K.

“GLM-4.5-Air 131K $0.14 $0.86”
USD 0.14not publishedUSD 0.86USD 0.32131,072not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
3Z.ai maker
GLM-4.5-Air
Notes and source quote
“| GLM-4.5-Air | $0.2 | $0.03 | Limited-time Free | $1.1 |”
USD 0.20USD 0.03USD 1.10USD 0.425not statednot statedZ.ai page
checked 2026-11-14
re-checked 2026-11-16
4GMI Cloud
zai-org/GLM-4.5-Air-FP8
Notes and source quote

No cache-read price published.

“Price (per 1M tokens) Input $0.20 Output $1.10”
USD 0.20not publishedUSD 1.10USD 0.425131,076FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does GLM 4.5 Air cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on GLM 4.5 Air, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Novita AIUSD 21.33USD 36.39USD 149.85
SiliconFlowUSD 28.08USD 46.50USD 329.40
Z.ai (maker)USD 28.62USD 52.26USD 198.90
GMI CloudUSD 37.80USD 64.50USD 459.00

For the support chatbot, the cheapest price (Novita AI, USD 21.33 a month) saves USD 7.02 against the median (USD 28.35). For the coding agent the gap is USD 114.30 a month (43% lower).

Which GLM 4.5 Air provider is cheapest for your traffic?

Novita AI has the lowest input price (USD 0.13) and the lowest output price (USD 0.85), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

GLM 4.5 Air: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Novita AIUSD 0.31 cheapestUSD 0.2706 cheapestUSD 0.2391 cheapest
SiliconFlow (no cache price)USD 0.32USD 0.32USD 0.32
Z.ai (maker)USD 0.425USD 0.3613USD 0.3103
GMI Cloud (no cache price)USD 0.425USD 0.425USD 0.425

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

2 of 4 providers publish a cached-input price below the input price: Novita AI (81% off), Z.ai (85% off). SiliconFlow and GMI Cloud publish none, so cached tokens there bill at the input price.

Context windows differ: 131,076 tokens at GMI Cloud; 131,072 tokens at Novita AI and SiliconFlow. Z.ai does not state one. The cheapest row is not always the one that fits a long prompt.

Estimate your own bill

The Z.ai models whose cheapest standard price is closest to GLM 4.5 Air's (USD 0.31 blended):

Z.ai models priced closest to GLM 4.5 Air
ModelCheapest inputCheapest outputMax contextProviders
GLM 4.6VUSD 0.30USD 0.90131,0722
GLM 5.3 FlashXUSD 0.37USD 1.251,048,5762
GLM 4.7 FlashUSD 0.06USD 0.40202,7526
GLM 4.7USD 0.40USD 1.75204,8008
GLM 4.6USD 0.43USD 1.75204,8006
GLM 5.3 FlashUSD 0.075USD 0.251,048,57620

Priced closest from other makers: Qwen3-VL 8B (Qwen, USD 0.305) · DeepSeek-V3.2-Exp (DeepSeek, USD 0.305) · Ripple-65B Preview (Ricursive AI, USD 0.30).

Compare GLM 4.5 Air with

Also compared: vs Qwen3.8 27B · vs GLM-4.5-FP8.

Every GLM 4.5 Air price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the GLM 4.5 Air API cost per token?

From USD 0.13 per 1M input tokens (USD 0.00000013 per token) and USD 0.85 per 1M output tokens (USD 0.00000085 per token) at the lowest standard prices we found. The median of 4 standard prices is USD 0.17 input and USD 0.98 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for GLM 4.5 Air?

Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Novita AI, ranked on a blend of 3 input tokens to 1 output token (USD 0.31 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is GLM 4.5 Air cheaper from a host than from Z.ai?

Yes. Novita AI charges USD 0.13 input and USD 0.85 output per 1M tokens, 27% below Z.ai's own USD 0.20 / USD 1.10 on the 3:1 blend.

Does GLM 4.5 Air have cached input pricing?

2 of 4 standard prices include one. The lowest is USD 0.025 per 1M at Novita AI; the median is USD 0.0275. Providers without one bill cached input at the input price. What cached input means.

What is the GLM 4.5 Air context window?

Up to 131,076 tokens. 2 standard prices come with less, down to 131,072 tokens (Novita AI and SiliconFlow). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on GLM 4.5 Air?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 149.85 a month at Novita AI, USD 264.15 at the median price and USD 459.00 at GMI Cloud. Try your own numbers.

Is GLM 4.5 Air free to use through an API?

No provider in our data lists a free price for GLM 4.5 Air as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is GLM 4.5 Air open source, with open weights, and what is its licence?

Z.ai publishes the weights on Hugging Face as zai-org/GLM-4.5-Air, in a public repository with no access gate. The licence, as the Z.ai model card metadata states it: MIT (mit). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Z.ai's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does GLM 4.5 Air have?

Total parameters, as the Z.ai model card states them: 106B. Active parameters per token: 12B. (checked 2026-11-16; BroadNet did not verify these figures.)

How do I call GLM 4.5 Air with the OpenAI SDK?

BroadNet does not serve GLM 4.5 Air. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: Z.ai (https://api.z.ai/api/paas/v4/, model GLM-4.5-Air). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity