InferIndex
Language, English, EN
Account

ModelsZ.aiGLM 4.5 Air

GLM 4.5 Air

z-ai/glm-4.5-air Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.315
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.425
Offers
25
Providers
17

Cheapest right now

$0.165 blended / 1M tokens

No change7D
in
$0.12
out
$0.301
Cached input
$0.024

prompt up to 32K (31,999) tokens: up to 32K (31,999): $0.12 / $0.301; up to 32K (31,999): $0.12 / $0.902; up to 128K (127,999): $0.18 / $1.20 (Input / Output, per million tokens)

See pricing See pricing at Zhipu AI (opens in a new tab)via Zhipu AI

Public leaderboards

  • Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control). #191 of 419Best rank in the source's rank spread, 191st to 206th, given the confidence intervals of all ranked models. 199th by score. 1,373 1,369 to 1,377Arena Score · 30,652 votes

Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours

GLM 4.5 Air costs from $0.165 per million tokens (at a 3:1 input:output mix): the cheapest of 8 comparable offers, at Zhipu AI, checked on ; 25 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.Official list price

Offers not counted in cheapest, median or most expensive (17)

  • $0.16 · ZenMux via ZenMux · price tiers could not be read
  • $0.165 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.31 · Embercloud via LLM API · cannot be designated the cheapest
  • $0.31 · Novita via Hugging Face · another route of the same provider
  • $0.31 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.31 · Glama via Glama · cannot be designated the cheapest
  • $0.31 · Martian via Martian · cannot be designated the cheapest
  • $0.31 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.31 · Novita via OpenRouter · another route of the same provider
  • $0.32 · FlexAI via Eden AI · cannot be designated the cheapest
  • $0.32 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
  • $0.352 · io.net · cannot be designated the cheapest
  • $0.425 · Z.AI via Eden AI · cannot be designated the cheapest
  • $0.425 · Z.AI via Kilo Gateway · cannot be designated the cheapest
  • $0.425 · Z.AI via LLM API · cannot be designated the cheapest
  • $0.425 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.425 · Z.AI via OpenRouter · another route of the same provider

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

Novita

directYou buy access straight from the company that runs the model on its servers. · bf16 · 131k

$0.31 blended / 1M tokens

in
$0.13
out
$0.85
Cached input
$0.025
See pricing See pricing at Novita (opens in a new tab)at Novita

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.16, ZenMux$0.165
2026-10-03$0.16, ZenMux$0.165
2026-10-04$0.16, ZenMux$0.165
2026-10-05$0.16, ZenMux$0.165
2026-10-06$0.16, ZenMux$0.165
2026-10-07$0.16, ZenMux$0.165
2026-10-08$0.16, ZenMux$0.165
2026-10-09$0.16, ZenMux$0.165
2026-10-10$0.16, ZenMux$0.165
2026-10-11$0.16, ZenMux$0.165
2026-10-12$0.16, ZenMux$0.165
2026-10-13$0.16, ZenMux$0.165
2026-10-14$0.164, Zhipu AI$0.165
2026-10-15$0.164, Zhipu AI$0.165
2026-10-16$0.16, ZenMux$0.165
2026-10-17$0.16, ZenMux$0.165
2026-10-18$0.16, ZenMux$0.165
2026-10-19$0.16, ZenMux$0.165
2026-10-20$0.16, ZenMux$0.165
2026-10-21$0.16, ZenMux$0.165
2026-10-22$0.16, ZenMux$0.165
2026-10-23$0.16, ZenMux$0.165
2026-10-24$0.16, ZenMux$0.165
2026-10-25$0.16, ZenMux$0.165
2026-10-26$0.16, ZenMux$0.165
2026-10-27$0.16, ZenMux$0.165
2026-10-28$0.16, ZenMux$0.165
2026-10-29$0.16, ZenMux$0.165
2026-10-30$0.16, ZenMux$0.165
2026-10-31$0.16, ZenMux$0.165

Cheapest offerOfficial list price

Offers

25 of 25 offers

Offers for GLM 4.5 Air, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 ZenMux 0.117 0.291 0.16  – 128k Unclear tiers: First price only; the seller's other price tiers could not be read. Never selected as cheapest.tiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
Go to offer at ZenMux (opens in a new tab)
2 Zhipu AI 0.12  0.301 0.165 – – prompt up to 32K (31,999) tokens: up to 32K (31,999): $0.12 / $0.301; up to 32K (31,999): $0.12 / $0.902; up to 128K (127,999): $0.18 / $1.20 (Input / Output, per million tokens)
See pricing at Zhipu AI (opens in a new tab)
3 ShengSuanYun 0.12  0.301 0.165 – 128k Unverified. No public page for this offer: listed, not designated cheapestThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
: ShengSuanYun (opens in a new tab). No public price page for this model
4 PPIO 0.18  0.301 0.21  – 131k
See pricing at PPIO (opens in a new tab)
5 Novita 0.13  0.85  0.31  bf16 131k
See pricing at Novita (opens in a new tab)
6 Embercloudvia LLM API 0.13  0.85  0.31  – – Unconfirmed. Last checked 18 October 2026: the last published value, not a confirmed one Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
See pricing at LLM API (opens in a new tab)
7 Novitavia Hugging Face 0.13  0.85  0.31  bf16 131k
See pricing at Hugging Face (opens in a new tab)
8 Novitavia Kilo Gateway 0.13  0.85  0.31  bf16 131k Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
9 Glama 0.13  0.85  0.31  – 131k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
10 Martian 0.13  0.85  0.31  – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
11 NanoGPT 0.13  0.85  0.31  – 128k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
Go to offer at NanoGPT (opens in a new tab)
12 Nous Portal 0.13  0.85  0.31  – 131k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
13 Novitavia OpenRouter 0.13  0.85  0.31  bf16 131k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
14 FlexAIvia Eden AI 0.14  0.86  0.32  fp8 131k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
15 SiliconFlowvia Kilo Gateway 0.14  0.86  0.32  fp8 131k Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
16 SiliconFlowvia OpenRouter 0.14  0.86  0.32  fp8 131k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
17 io.net 0.157 0.937 0.352 – 131k Unverified. No public page for this offer: listed, not designated cheapest
: io.net (opens in a new tab). No public price page for this model
18 Z.AIvia Eden AI 0.20  1.10  0.425 fp8 131k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
19 Z.AIvia Kilo Gateway 0.20  1.10  0.425 fp8 131k Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
20 Z.AIvia LLM API 0.20  1.10  0.425 fp8 – Unconfirmed. Last checked 18 October 2026: the last published value, not a confirmed one Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
See pricing at LLM API (opens in a new tab)
21 OrcaRouter 0.20  1.10  0.425 – 128k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at OrcaRouter (opens in a new tab)
22 Vercel AI Gateway 0.20  1.10  0.425 – –
Go to offer at Vercel AI Gateway (opens in a new tab)
23 Z.AIvia LLM Gateway 0.20  1.10  0.425 fp8 – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
24 DeepInfravia Requesty 0.20  1.10  0.425 – 131k United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
25 Z.AIvia OpenRouter 0.20  1.10  0.425 fp8 131k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

  • ZenMux

    $0.16

    ZenMux

    in
    $0.117
    out
    $0.291
    Precision
    –
    Context
    128k

    Prompts may be used for trainingUnclear tiers: First price only; the seller's other price tiers could not be read. Never selected as cheapest.tiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.

    Go to offer Go to offer at ZenMux (opens in a new tab)via ZenMux

  • Zhipu AI

    $0.165

    Zhipu AI

    in
    $0.12 
    out
    $0.301
    Precision
    –
    Context
    –

    Prompts may be used for trainingprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.12 / $0.301; up to 32K (31,999): $0.12 / $0.902; up to 128K (127,999): $0.18 / $1.20 (Input / Output, per million tokens)

    See pricing See pricing at Zhipu AI (opens in a new tab)via Zhipu AI

  • ShengSuanYun

    $0.165

    ShengSuanYun

    in
    $0.12 
    out
    $0.301
    Precision
    –
    Context
    128k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapestThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists

    Seller's site: ShengSuanYun (opens in a new tab)No public price page for this model

  • PPIO

    $0.21

    direct

    in
    $0.18 
    out
    $0.301
    Precision
    –
    Context
    131k

    Prompts may be used for training

    See pricing See pricing at PPIO (opens in a new tab)at PPIO

  • Novita

    $0.31

    direct

    in
    $0.13 
    out
    $0.85 
    Precision
    bf16
    Context
    131k

    No training on prompts

    See pricing See pricing at Novita (opens in a new tab)at Novita

  • Embercloud

    $0.31

    LLM API

    in
    $0.13 
    out
    $0.85 
    Precision
    –
    Context
    –

    Training terms not publishedUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed oneUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • Novita

    $0.31

    Hugging Face

    in
    $0.13 
    out
    $0.85 
    Precision
    bf16
    Context
    131k

    No training on prompts

    See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

  • Novita

    $0.31

    Kilo Gateway

    in
    $0.13 
    out
    $0.85 
    Precision
    bf16
    Context
    131k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Glama

    $0.31

    Glama

    in
    $0.13 
    out
    $0.85 
    Precision
    –
    Context
    131k

    No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    Seller's site: Glama (opens in a new tab)No public price page for this model

  • Martian

    $0.31

    Martian

    in
    $0.13 
    out
    $0.85 
    Precision
    –
    Context
    –

    Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Martian (opens in a new tab)via Martian

  • NanoGPT

    $0.31

    NanoGPT

    in
    $0.13 
    out
    $0.85 
    Precision
    –
    Context
    128k

    No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists

    Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

  • Nous Portal

    $0.31

    Nous Portal

    in
    $0.13 
    out
    $0.85 
    Precision
    –
    Context
    131k

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Nous Portal (opens in a new tab)via Nous Portal

  • Novita

    $0.31

    OpenRouter

    in
    $0.13 
    out
    $0.85 
    Precision
    bf16
    Context
    131k

    No training on promptsFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • FlexAI

    $0.32

    Eden AI

    in
    $0.14 
    out
    $0.86 
    Precision
    fp8
    Context
    131k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • SiliconFlow

    $0.32

    Kilo Gateway

    in
    $0.14 
    out
    $0.86 
    Precision
    fp8
    Context
    131k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • SiliconFlow

    $0.32

    OpenRouter

    in
    $0.14 
    out
    $0.86 
    Precision
    fp8
    Context
    131k

    Training terms not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • io.net

    $0.352

    direct

    in
    $0.157
    out
    $0.937
    Precision
    –
    Context
    131k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: io.net (opens in a new tab)No public price page for this model

  • Z.AI

    $0.425

    Eden AI

    in
    $0.20 
    out
    $1.10 
    Precision
    fp8
    Context
    131k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • Z.AI

    $0.425

    Kilo Gateway

    in
    $0.20 
    out
    $1.10 
    Precision
    fp8
    Context
    131k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Z.AI

    $0.425

    LLM API

    in
    $0.20 
    out
    $1.10 
    Precision
    fp8
    Context
    –

    Prompts may be used for trainingUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed oneUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • OrcaRouter

    $0.425

    OrcaRouter

    in
    $0.20 
    out
    $1.10 
    Precision
    –
    Context
    128k

    Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    Go to offer Go to offer at OrcaRouter (opens in a new tab)via OrcaRouter

  • Vercel AI Gateway

    $0.425

    Vercel AI Gateway

    in
    $0.20 
    out
    $1.10 
    Precision
    –
    Context
    –

    No training on prompts

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • Z.AI

    $0.425

    LLM Gateway

    in
    $0.20 
    out
    $1.10 
    Precision
    fp8
    Context
    –

    Prompts may be used for trainingFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

    Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

  • DeepInfra

    $0.425

    Requesty

    in
    $0.20 
    out
    $1.10 
    Precision
    –
    Context
    131k

    Prompts may be used for trainingUnited StatesFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

  • Z.AI

    $0.425

    OpenRouter

    in
    $0.20 
    out
    $1.10 
    Precision
    fp8
    Context
    131k

    Prompts may be used for trainingFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. PPIO$15.33per month
  2. Novita$20.55per month+$5.22 vs the cheapest
  3. NanoGPT$20.55per month+$5.22 vs the cheapest

Host it yourself instead? See the break-even

Compare GLM 4.5 Air with

Related models

More from Z.ai

All Z.ai models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=z-ai/glm-4.5-air
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.