GLM 4.5V
z-ai/glm-4.5v 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.
- $0.90
- 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.
- $0.902
- Offers
- 17
- Providers
- 8
Cheapest right now
$0.451 blended / 1M tokens
-49.9%7D- in
- $0.301
- out
- $0.902
- Cached input
- $0.06
prompt up to 32K (31,999) tokens: up to 32K (31,999): $0.301 / $0.902; up to 64K (63,999): $0.601 / $1.80 (Input / Output, per million tokens)
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). #204 of 419Best rank in the source's rank spread, 204th to 239th, given the confidence intervals of all ranked models. 218th by score. 1,352 1,344 to 1,361Arena Score · 4,817 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 4.5V costs from $0.451 per million tokens (at a 3:1 input:output mix): the cheapest of 6 comparable offers, at Zhipu AI, checked on ; 17 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 priceOffers not counted in cheapest, median or most expensive (11)
- $0.90 · Novita via Hugging Face · another route of the same provider
- $0.90 · Novita via Kilo Gateway · cannot be designated the cheapest
- $0.90 · Novita via LLM API · cannot be designated the cheapest
- $0.90 · Z.AI via Eden AI · cannot be designated the cheapest
- $0.90 · Z.AI via Kilo Gateway · cannot be designated the cheapest
- $0.90 · Z.AI via LLM API · cannot be designated the cheapest
- $0.90 · Glama via Glama · cannot be designated the cheapest
- $0.90 · Nous Portal via Nous Portal · cannot be designated the cheapest
- $0.90 · Novita via LLM Gateway · another route of the same provider
- $0.90 · Novita via OpenRouter · another route of the same provider
- $0.90 · 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.
$0.90 blended / 1M tokens
- in
- $0.60
- out
- $1.80
- Cached input
- $0.11
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.
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-25 | $0.90, PPIO | $0.451 |
| 2026-10-26 | $0.90, PPIO | $0.451 |
| 2026-10-27 | $0.45, Zhipu AI | $0.451 |
| 2026-10-28 | $0.45, Zhipu AI | $0.451 |
| 2026-10-29 | $0.45, Zhipu AI | $0.451 |
| 2026-10-30 | $0.45, Zhipu AI | $0.451 |
| 2026-10-31 | $0.451, Zhipu AI | $0.451 |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-02 | $0.895, PPIO | $0.451 |
| 2026-10-03 | $0.895, PPIO | $0.451 |
| 2026-10-04 | $0.895, PPIO | $0.451 |
| 2026-10-05 | $0.895, PPIO | $0.451 |
| 2026-10-06 | $0.447, Zhipu AI | $0.451 |
| 2026-10-07 | $0.447, Zhipu AI | $0.451 |
| 2026-10-08 | $0.447, Zhipu AI | $0.451 |
| 2026-10-09 | $0.448, Zhipu AI | $0.451 |
| 2026-10-10 | $0.448, Zhipu AI | $0.451 |
| 2026-10-11 | $0.448, Zhipu AI | $0.451 |
| 2026-10-12 | $0.448, Zhipu AI | $0.451 |
| 2026-10-13 | $0.448, Zhipu AI | $0.451 |
| 2026-10-14 | $0.448, Zhipu AI | $0.451 |
| 2026-10-15 | $0.448, Zhipu AI | $0.451 |
| 2026-10-16 | $0.448, Zhipu AI | $0.451 |
| 2026-10-17 | $0.449, Zhipu AI | $0.451 |
| 2026-10-18 | $0.449, Zhipu AI | $0.451 |
| 2026-10-19 | $0.449, Zhipu AI | $0.451 |
| 2026-10-20 | $0.449, Zhipu AI | $0.451 |
| 2026-10-21 | $0.899, PPIO | $0.451 |
| 2026-10-22 | $0.899, PPIO | $0.451 |
| 2026-10-23 | $0.899, PPIO | $0.451 |
| 2026-10-24 | $0.90, PPIO | $0.451 |
| 2026-10-25 | $0.90, PPIO | $0.451 |
| 2026-10-26 | $0.90, PPIO | $0.451 |
| 2026-10-27 | $0.45, Zhipu AI | $0.451 |
| 2026-10-28 | $0.45, Zhipu AI | $0.451 |
| 2026-10-29 | $0.45, Zhipu AI | $0.451 |
| 2026-10-30 | $0.45, Zhipu AI | $0.451 |
| 2026-10-31 | $0.451, Zhipu AI | $0.451 |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-01 | $0.895, PPIO | $0.451 |
| 2026-10-02 | $0.895, PPIO | $0.451 |
| 2026-10-03 | $0.895, PPIO | $0.451 |
| 2026-10-04 | $0.895, PPIO | $0.451 |
| 2026-10-05 | $0.895, PPIO | $0.451 |
| 2026-10-06 | $0.447, Zhipu AI | $0.451 |
| 2026-10-07 | $0.447, Zhipu AI | $0.451 |
| 2026-10-08 | $0.447, Zhipu AI | $0.451 |
| 2026-10-09 | $0.448, Zhipu AI | $0.451 |
| 2026-10-10 | $0.448, Zhipu AI | $0.451 |
| 2026-10-11 | $0.448, Zhipu AI | $0.451 |
| 2026-10-12 | $0.448, Zhipu AI | $0.451 |
| 2026-10-13 | $0.448, Zhipu AI | $0.451 |
| 2026-10-14 | $0.448, Zhipu AI | $0.451 |
| 2026-10-15 | $0.448, Zhipu AI | $0.451 |
| 2026-10-16 | $0.448, Zhipu AI | $0.451 |
| 2026-10-17 | $0.449, Zhipu AI | $0.451 |
| 2026-10-18 | $0.449, Zhipu AI | $0.451 |
| 2026-10-19 | $0.449, Zhipu AI | $0.451 |
| 2026-10-20 | $0.449, Zhipu AI | $0.451 |
| 2026-10-21 | $0.899, PPIO | $0.451 |
| 2026-10-22 | $0.899, PPIO | $0.451 |
| 2026-10-23 | $0.899, PPIO | $0.451 |
| 2026-10-24 | $0.90, PPIO | $0.451 |
| 2026-10-25 | $0.90, PPIO | $0.451 |
| 2026-10-26 | $0.90, PPIO | $0.451 |
| 2026-10-27 | $0.45, Zhipu AI | $0.451 |
| 2026-10-28 | $0.45, Zhipu AI | $0.451 |
| 2026-10-29 | $0.45, Zhipu AI | $0.451 |
| 2026-10-30 | $0.45, Zhipu AI | $0.451 |
| 2026-10-31 | $0.451, Zhipu AI | $0.451 |
Cheapest offerOfficial list price
| Rank | Provider · 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 $/1M | Output $/1M | Blended $/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. | Signals | Offer |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 0.301 | 0.902 | 0.451 | – | – | prompt up to 32K (31,999) tokens: up to 32K (31,999): $0.301 / $0.902; up to 64K (63,999): $0.601 / $1.80 (Input / Output, per million tokens) | |||
| 2 | 0.60 | 1.80 | 0.90 | fp8 | 66k | ||||
| 3 | 0.60 | 1.80 | 0.90 | fp8 | 66k | ||||
| 4 | 0.60 | 1.80 | 0.90 | fp8 | 66k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 5 | 0.60 | 1.80 | 0.90 | 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 | ||
| 6 | 0.60 | 1.80 | 0.90 | fp8 | 66k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 7 | 0.60 | 1.80 | 0.90 | fp8 | 66k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 8 | 0.60 | 1.80 | 0.90 | 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 | ||
| 9 | 0.60 | 1.80 | 0.90 | – | 66k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 10 | 0.60 | 1.80 | 0.90 | – | 66k | Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists | |||
| 11 | 0.60 | 1.80 | 0.90 | – | 66k | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 12 | 0.60 | 1.80 | 0.90 | – | – | ||||
| 13 | 0.60 | 1.80 | 0.90 | 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. | |||
| 14 | 0.60 | 1.80 | 0.90 | 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. | |||
| 15 | 0.60 | 1.80 | 0.90 | fp8 | 66k | 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. | |||
| 16 | 0.60 | 1.80 | 0.90 | fp8 | 66k | 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. | |||
| 17 | 0.601 | 1.80 | 0.902 | – | 66k |
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.
-
$0.451Zhipu AI
Zhipu AI
- in
- $0.301
- out
- $0.902
- Precision
- –
- Context
- –
Prompts may be used for trainingprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.301 / $0.902; up to 64K (63,999): $0.601 / $1.80 (Input / Output, per million tokens)
-
$0.90Novita
direct
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
No training on prompts
-
$0.90Novita
Hugging Face
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
No training on prompts
See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face -
$0.90Novita
Kilo Gateway
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
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 -
$0.90Novita
LLM API
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- –
No training on promptsUnconfirmed. 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
-
$0.90Z.AI
Eden AI
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
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 -
$0.90Z.AI
Kilo Gateway
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
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 -
$0.90Z.AI
LLM API
- in
- $0.60
- out
- $1.80
- 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
-
$0.90Glama
Glama
- in
- $0.60
- out
- $1.80
- Precision
- –
- Context
- 66k
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 -
$0.90NanoGPT
NanoGPT
- in
- $0.60
- out
- $1.80
- Precision
- –
- Context
- 66k
No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
-
$0.90Nous Portal
Nous Portal
- in
- $0.60
- out
- $1.80
- Precision
- –
- Context
- 66k
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 -
$0.90Vercel AI Gateway
Vercel AI Gateway
- in
- $0.60
- out
- $1.80
- 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 -
$0.90Novita
LLM Gateway
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- –
No training on promptsFee 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 -
$0.90Z.AI
LLM Gateway
- in
- $0.60
- out
- $1.80
- 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 -
$0.90Novita
OpenRouter
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
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.
-
$0.90Z.AI
OpenRouter
- in
- $0.60
- out
- $1.80
- Precision
- fp8
- Context
- 66k
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.
-
$0.902PPIO
direct
- in
- $0.601
- out
- $1.80
- Precision
- –
- Context
- 66k
Prompts may be used for training
No offer matches these filters.
Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.
Monthly cost for your workload
Computed by the API for the three cheapest offers, per 30-day month.- Zhipu AI$31.57per month
- Novita$63.00per month+$31.43 vs the cheapest
- NanoGPT$63.00per month+$31.43 vs the cheapest
The estimate could not be updated. Try again in a moment.
Compare GLM 4.5V with
Related models
More from Z.ai
Same index family
Use this data
The index is queryable. The API is free to use.curl https://api.inferindex.dev/cheapest?model=z-ai/glm-4.5vclaude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp