InferIndex
Language, English, EN
Account

ModelsZ.aiGLM 4.6

GLM 4.6

z-ai/glm-4.6198k context 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.
$0.963
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.
$1.50
Offers
44
Providers
22

Cheapest right now

Venice

The provider's published policy: prompts are not used for training.

directYou buy access straight from the company that runs the model on its servers. · fp4 · 198k

$0.76 blended / 1M tokens

No change7D
in
$0.43
out
$1.75
Cached input
$0.08
See pricing See pricing at Venice (opens in a new tab)at Venice

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). #111 of 419Best rank in the source's rank spread, 111th to 144th, given the confidence intervals of all ranked models. 128th by score. 1,424 1,420 to 1,428Arena Score · 35,810 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #117 of 152Best rank in the source's rank spread, 117th to 129th, given the confidence intervals of all ranked models. 124th by score. 1,341 1,330 to 1,352Arena Score · 6,755 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 4.6 costs from $0.76 per million tokens (at a 3:1 input:output mix): the cheapest of 10 comparable offers, at Venice, checked on ; 44 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.

Offers not counted in cheapest, median or most expensive (34)

  • $0.51 · ZenMux via ZenMux · price tiers could not be read
  • $0.526 · UCloud · cannot be designated the cheapest
  • $0.526 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.758 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.76 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $0.76 · Martian via Martian · cannot be designated the cheapest
  • $0.76 · Venice via OpenRouter · another route of the same provider
  • $0.825 · Alibaba via LLM Gateway · cannot be designated the cheapest
  • $0.875 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.875 · DeepInfra via Hugging Face · another route of the same provider
  • $0.875 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.875 · DeepInfra via Vercel AI Gateway · another route of the same provider
  • $0.875 · Glama via Glama · cannot be designated the cheapest
  • $0.875 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.875 · DeepInfra via OpenRouter · another route of the same provider
  • $0.899 · io.net · cannot be designated the cheapest
  • $0.95 · AtlasCloud via LMRouter · cannot be designated the cheapest
  • $0.963 · Novita via Hugging Face · another route of the same provider
  • $0.963 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.963 · Novita via LLM API · cannot be designated the cheapest
  • $0.963 · Novita via Vercel AI Gateway · another route of the same provider
  • $0.963 · Novita via LLM Gateway · another route of the same provider
  • $0.963 · Novita via OpenRouter · another route of the same provider
  • $1.00 · Z.AI via Eden AI · cannot be designated the cheapest
  • $1.00 · Z.AI via Kilo Gateway · cannot be designated the cheapest
  • $1.00 · Z.AI via LLM API · cannot be designated the cheapest
  • $1.00 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $1.00 · Z.AI via LLM Gateway · another route of the same provider
  • $1.00 · Novita via Requesty · another route of the same provider
  • $1.00 · Z.AI via Requesty · another route of the same provider
  • $1.00 · Z.AI via OpenRouter · another route of the same provider
  • $1.01 · Poe via Poe · price converted from points
  • $1.29 · Qiniu · cannot be designated the cheapest
  • $2.38 · Cerebras via LLM Gateway · cannot be designated the cheapest

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$0.509, ZenMux–
2026-10-03$0.509, ZenMux–
2026-10-04$0.509, ZenMux–
2026-10-05$0.509, ZenMux–
2026-10-06$0.509, ZenMux–
2026-10-07$0.509, ZenMux–
2026-10-08$0.509, ZenMux–
2026-10-09$0.509, ZenMux–
2026-10-10$0.509, ZenMux–
2026-10-11$0.509, ZenMux–
2026-10-12$0.509, ZenMux–
2026-10-13$0.509, ZenMux–
2026-10-14$0.523, UCloud–
2026-10-15$0.523, UCloud–
2026-10-16$0.509, ZenMux–
2026-10-17$0.509, ZenMux–
2026-10-18$0.509, ZenMux–
2026-10-19$0.51, ZenMux–
2026-10-20$0.51, ZenMux–
2026-10-21$0.51, ZenMux–
2026-10-22$0.51, ZenMux–
2026-10-23$0.51, ZenMux–
2026-10-24$0.51, ZenMux–
2026-10-25$0.51, ZenMux–
2026-10-26$0.51, ZenMux–
2026-10-27$0.51, ZenMux–
2026-10-28$0.51, ZenMux–
2026-10-29$0.51, ZenMux–
2026-10-30$0.51, ZenMux–
2026-10-31$0.51, ZenMux–

Cheapest offer

Offers

The 25 cheapest of 44 offers

Offers for GLM 4.6, 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 0.291 1.16 0.51  – 200k 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 UCloud 0.301 1.20 0.526 – – Unverified. No public page for this offer: listed, not designated cheapesttiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
: UCloud (opens in a new tab). No public price page for this model
3 ShengSuanYun 0.301 1.20 0.526 – 200k 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 FastRouter 0.43  1.74 0.758 – 203k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at FastRouter (opens in a new tab)
5 Venice 0.43  1.75 0.76  fp4 198k
See pricing at Venice (opens in a new tab)
6 Venicevia Kilo Gateway 0.43  1.75 0.76  fp4 198k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
7 Martian 0.43  1.75 0.76  – – 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)
8 Venicevia OpenRouter 0.43  1.75 0.76  fp4 198k 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)
9 Alibabavia LLM Gateway 0.431 2.01 0.825 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)
10 Neosantara 0.551 1.65 0.827 – 128k Singapore, Indonesia, United States
See pricing at Neosantara (opens in a new tab)
11 DeepInfra 0.50  2.00 0.875 fp4 203k United States
Go to offer at DeepInfra (opens in a new tab)
12 DeepInfravia Eden AI 0.50  2.00 0.875 fp4 203k United States 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
13 DeepInfravia Hugging Face 0.50  2.00 0.875 fp4 203k United States
See pricing at Hugging Face (opens in a new tab)
14 DeepInfravia Kilo Gateway 0.50  2.00 0.875 fp4 203k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
15 DeepInfravia Vercel AI Gateway 0.50  2.00 0.875 fp4 203k United States
Go to offer at Vercel AI Gateway (opens in a new tab)
16 Glama 0.50  2.00 0.875 – 200k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
17 NanoGPT 0.50  2.00 0.875 – 200k 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)
18 Nous Portal 0.50  2.00 0.875 – 205k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 10 price changes in 7 days. Over that period: input $0.43 – $0.55, output $1.75 – $2.20 per million tokens. An offer whose price changes this often is not selected as the cheapest.
See pricing at Nous Portal (opens in a new tab)
19 DeepInfravia OpenRouter 0.50  2.00 0.875 fp4 203k United States 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)
20 io.net 0.52  2.04 0.899 – 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
21 AtlasCloudvia LMRouter 0.60  2.00 0.95  fp8 203k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
See pricing at LMRouter (opens in a new tab)
22 Featherless 0.55  2.20 0.963 – 203k
Go to offer at Featherless (opens in a new tab)
23 Novita 0.55  2.20 0.963 bf16 205k
See pricing at Novita (opens in a new tab)
24 Novitavia Hugging Face 0.55  2.20 0.963 bf16 205k
See pricing at Hugging Face (opens in a new tab)
25 Novitavia Kilo Gateway 0.55  2.20 0.963 bf16 205k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (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

    $0.51

    ZenMux

    in
    $0.291
    out
    $1.16
    Precision
    –
    Context
    200k

    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

  • UCloud

    $0.526

    direct

    in
    $0.301
    out
    $1.20
    Precision
    –
    Context
    –

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapesttiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.

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

  • ShengSuanYun

    $0.526

    ShengSuanYun

    in
    $0.301
    out
    $1.20
    Precision
    –
    Context
    200k

    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

  • FastRouter

    $0.758

    FastRouter

    in
    $0.43 
    out
    $1.74
    Precision
    –
    Context
    203k

    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 FastRouter (opens in a new tab)via FastRouter

  • Venice

    $0.76

    direct

    in
    $0.43 
    out
    $1.75
    Precision
    fp4
    Context
    198k

    No training on prompts

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

  • Venice

    $0.76

    Kilo Gateway

    in
    $0.43 
    out
    $1.75
    Precision
    fp4
    Context
    198k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

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

  • Martian

    $0.76

    Martian

    in
    $0.43 
    out
    $1.75
    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

  • Venice

    $0.76

    OpenRouter

    in
    $0.43 
    out
    $1.75
    Precision
    fp4
    Context
    198k

    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

  • Alibaba

    $0.825

    LLM Gateway

    in
    $0.431
    out
    $2.01
    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

  • Neosantara

    $0.827

    Neosantara

    in
    $0.551
    out
    $1.65
    Precision
    –
    Context
    128k

    Training terms not publishedSingapore, Indonesia, United States

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

  • DeepInfra

    $0.875

    direct

    in
    $0.50 
    out
    $2.00
    Precision
    fp4
    Context
    203k

    No training on promptsUnited States

    Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

  • DeepInfra

    $0.875

    Eden AI

    in
    $0.50 
    out
    $2.00
    Precision
    fp4
    Context
    203k

    Prompts may be used for trainingUnited StatesUnverified. 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

  • DeepInfra

    $0.875

    Hugging Face

    in
    $0.50 
    out
    $2.00
    Precision
    fp4
    Context
    203k

    No training on promptsUnited States

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

  • DeepInfra

    $0.875

    Kilo Gateway

    in
    $0.50 
    out
    $2.00
    Precision
    fp4
    Context
    203k

    Training terms not publishedUnited StatesUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

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

  • DeepInfra

    $0.875

    Vercel AI Gateway

    in
    $0.50 
    out
    $2.00
    Precision
    fp4
    Context
    203k

    No training on promptsUnited States

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

  • Glama

    $0.875

    Glama

    in
    $0.50 
    out
    $2.00
    Precision
    –
    Context
    200k

    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

  • NanoGPT

    $0.875

    NanoGPT

    in
    $0.50 
    out
    $2.00
    Precision
    –
    Context
    200k

    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

    $0.875

    Nous Portal

    in
    $0.50 
    out
    $2.00
    Precision
    –
    Context
    205k

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 10 price changes in 7 days. Over that period: input $0.43 – $0.55, output $1.75 – $2.20 per million tokens. An offer whose price changes this often is not selected as the cheapest.backend 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

  • DeepInfra

    $0.875

    OpenRouter

    in
    $0.50 
    out
    $2.00
    Precision
    fp4
    Context
    203k

    No training on promptsUnited StatesFee 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

    $0.899

    direct

    in
    $0.52 
    out
    $2.04
    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

  • AtlasCloud

    $0.95

    LMRouter

    in
    $0.60 
    out
    $2.00
    Precision
    fp8
    Context
    203k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

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

  • Featherless

    $0.963

    direct

    in
    $0.55 
    out
    $2.20
    Precision
    –
    Context
    203k

    Training terms not published

    Go to offer Go to offer at Featherless (opens in a new tab)at Featherless

  • Novita

    $0.963

    direct

    in
    $0.55 
    out
    $2.20
    Precision
    bf16
    Context
    205k

    No training on prompts

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

  • Novita

    $0.963

    Hugging Face

    in
    $0.55 
    out
    $2.20
    Precision
    bf16
    Context
    205k

    No training on prompts

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

  • Novita

    $0.963

    Kilo Gateway

    in
    $0.55 
    out
    $2.20
    Precision
    bf16
    Context
    205k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway
Show all 44 offers

3 flex or batch offers hidden (lower priority, variable latency).

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. Venice$52.05per month
  2. Neosantara$57.86per month+$5.81 vs the cheapest
  3. DeepInfra$60.00per month+$7.95 vs the cheapest

Host it yourself instead? See the break-even

Compare GLM 4.6 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-4.6
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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