BroadRouter

GLM 5 API pricing

Updated

The cheapest standard price for GLM 5 is GMI Cloud (promotional) at USD 0.60 per 1M input tokens and USD 1.92 per 1M output tokens. The median across 10 standard prices is USD 1 / USD 3.20. Z.ai's own API charges USD 1 / USD 3.20. Every price is read from the provider's own pricing page, checked 2026-11-15.

Z.ai · slug glm-5 · up to 204,800 tokens of context · 10 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 2026-03-02 (7 archived price points, 0 list-price changes): LLM API price history.

What does Z.ai charge for GLM 5?

Input
USD 1
Cached input
USD 0.20
Output
USD 3.20
Blended 3:1
USD 1.55

USD per 1M tokens on Z.ai, model GLM-5, standard tier. Source, checked 2026-11-14.

Is a host cheaper than Z.ai? Yes. GMI Cloud charges USD 0.60 input and USD 1.92 output per 1M tokens, 40% below Z.ai's own USD 1 / USD 3.20 on the 3:1 blend (a promotional price).

GLM 5 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 67% above the cheapest.

GLM 5 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1GMI Cloud cheapest promo
zai-org/GLM-5-FP8
Notes and source quote

Promotional price, 40% off list (list 1 in / 3.2 out / 0.2 cached).

“Price (per 1M tokens) 40% off Input $0.60 $1.00 Output $1.92 $3.20 Cache Read $0.12 $0.20 Cache Write -”
USD 0.60USD 0.12USD 1.92USD 0.93202,752FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
2SiliconFlow
Notes and source quote

Context shown as 205K.

“GLM-5 205K $0.95 $0.2 $2.55”
USD 0.95USD 0.20USD 2.55USD 1.35204,800not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
3Featherless
zai-org/GLM-5
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.95 / CACHED $0.19 / OUTPUT $3.15”
USD 0.95USD 0.19USD 3.15USD 1.50202,752FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
4Z.ai maker
GLM-5
Notes and source quote
“| GLM-5 | $1 | $0.2 | Limited-time Free | $3.2 |”
USD 1USD 0.20USD 3.20USD 1.55not statednot statedZ.ai page
checked 2026-11-14
re-checked 2026-11-16
5Amazon Bedrock
Notes and source quote

Table headed "Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)".

“GLM 5 $ 1.00 $ 3.20”
USD 1not publishedUSD 3.20USD 1.55not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
6Baidu
glm-5
Notes and source quote
“GLM-5 GLM-5 Inference Service Input 1.0 $/M tokens Cache Hit 0.2 $/M tokens Output 3.2 $/M tokens”
USD 1USD 0.20USD 3.20USD 1.55198,000not statedBaidu page
checked 2026-11-15
re-checked 2026-11-16
7Google Vertex AI
glm-5
Notes and source quote
“GLM-5 Input $1.00 … Output $3.20 … Cache Hit $0.10”
USD 1USD 0.10USD 3.20USD 1.55not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
8Novita AI
zai-org/glm-5
Notes and source quote
“GLM 5 198K $1 /Mt · Cache Read $0.2 /Mt $3.2 /Mt”
USD 1USD 0.20USD 3.20USD 1.55202,800not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
9Parasail
Notes and source quote
“GLM-5 $1.00 $3.20 $0.20”
USD 1USD 0.20USD 3.20USD 1.55not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
10Venice
zai-org-glm-5
Notes and source quote
“| GLM 5 | `zai-org-glm-5` | $1.00 | $3.20 | $0.20 | — | Private |”
USD 1USD 0.20USD 3.20USD 1.55198,000FP8Venice 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 5 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 5, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
GMI Cloud (promo)USD 62.64USD 138.24USD 518.40
SiliconFlowUSD 90.90USD 212.25USD 792.00
FeatherlessUSD 101.16USD 220.53USD 830.70
Z.ai (maker)USD 104.40USD 230.40USD 864.00
Amazon BedrockUSD 147.60USD 288.00USD 2,088
BaiduUSD 104.40USD 230.40USD 864.00
Google Vertex AIUSD 99.00USD 223.20USD 711.00
Novita AIUSD 104.40USD 230.40USD 864.00
ParasailUSD 104.40USD 230.40USD 864.00
VeniceUSD 104.40USD 230.40USD 864.00

For the support chatbot, the cheapest price (GMI Cloud, USD 62.64 a month) saves USD 41.76 against the median (USD 104.40). For the coding agent the gap is USD 345.60 a month (40% lower).

Which GLM 5 provider is cheapest for your traffic?

GMI Cloud has the lowest input price (USD 0.60) and the lowest output price (USD 1.92), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

GLM 5: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
GMI CloudUSD 0.93 cheapestUSD 0.75 cheapestUSD 0.606 cheapest
SiliconFlowUSD 1.35USD 1.069USD 0.8438
FeatherlessUSD 1.50USD 1.215USD 0.987
Z.ai (maker)USD 1.55USD 1.25USD 1.01
Amazon Bedrock (no cache price)USD 1.55USD 1.55USD 1.55
BaiduUSD 1.55USD 1.25USD 1.01

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 4 dearer providers are in the price table above. 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.

9 of 10 providers publish a cached-input price below the input price: GMI Cloud (80% off), SiliconFlow (79% off), Featherless (80% off), Z.ai (80% off), Baidu (80% off) and 4 more. Amazon Bedrock publishes none, so cached tokens there bill at the input price.

Context windows differ: 204,800 tokens at SiliconFlow; 202,800 tokens at Novita AI; 202,752 tokens at GMI Cloud and Featherless; 198,000 tokens at Baidu and Venice. Z.ai, Amazon Bedrock, Google Vertex AI and Parasail do not state one. The cheapest row is not always the one that fits a long prompt.

What does GLM 5 cost in other languages?

The same text needs a different number of tokens in each language. With the GLM 5.3 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for GLM 5:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.206Featherless
Arabic MSAUSD 0.393Featherless
HindiUSD 0.850Featherless
ChineseUSD 0.564Featherless
CodeUSD 0.242Featherless

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Published benchmark results

BroadNet did not run these benchmarks; results are as published by the Z.ai model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site.

Published benchmark results for GLM 5, with sources
BenchmarkResultSetting or noteSource
GPQA-Diamond86.0not statedZ.ai model card, checked 2026-11-16
SWE-bench Verified77.8not statedZ.ai model card, checked 2026-11-16
HLE30.5not statedZ.ai model card, checked 2026-11-16
τ²-Bench89.7not statedZ.ai model card, checked 2026-11-16
GPQA Diamond0.878Setting as listed by Epoch (no suffix); Epoch run glm-5, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16

Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

Estimate your own bill

The Z.ai models whose cheapest standard price is closest to GLM 5's (USD 0.93 blended):

Z.ai models priced closest to GLM 5
ModelCheapest inputCheapest outputMax contextProviders
GLM 4.5VUSD 0.60USD 1.8065,5362
GLM 5.2USD 0.5625USD 1.801,048,57619
GLM-4.5-FP8USD 0.60USD 2.20131,0722
GLM 5.3USD 0.5625USD 2.501,048,57624
GLM 4.6USD 0.43USD 1.75204,8006
GLM 4.7USD 0.40USD 1.75204,8008

Priced closest from other makers: DeepSeek R1 (DeepSeek, USD 0.92) · NVIDIA Nemotron 3 Ultra (NVIDIA, USD 0.9125) · Kimi K2 Thinking (Moonshot AI, USD 0.90).

Compare GLM 5 with

Also compared: vs GLM 4.7 · vs GLM 5.1.

Every GLM 5 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 5 API cost per token?

From USD 0.60 per 1M input tokens (USD 0.0000006 per token) and USD 1.92 per 1M output tokens (USD 0.00000192 per token) at the cheapest standard price. The median of 10 standard prices is USD 1 input and USD 3.20 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 5?

GMI Cloud (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 0.93 per 1M). It is also the cheapest on both input and output. Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is GLM 5 cheaper from a host than from Z.ai?

Yes. GMI Cloud charges USD 0.60 input and USD 1.92 output per 1M tokens, 40% below Z.ai's own USD 1 / USD 3.20 on the 3:1 blend (a promotional price).

Does GLM 5 have cached input pricing?

9 of 10 standard prices include one. The lowest is USD 0.10 per 1M at Google Vertex AI; the median is USD 0.20. Providers without one bill cached input at the input price. What cached input means.

What is the GLM 5 context window?

Up to 204,800 tokens. 5 standard prices come with less, down to 198,000 tokens (Baidu, Venice, Featherless, GMI Cloud and Novita AI). 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 5?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 518.40 a month at GMI Cloud, USD 864.00 at the median price and USD 2,088 at Amazon Bedrock. Try your own numbers.

Is GLM 5 free to use through an API?

No provider in our data lists a free price for GLM 5 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.

How does GLM 5 score on benchmarks?

As published, the Z.ai model card reports 86.0 on GPQA-Diamond and 77.8 on SWE-bench Verified; Epoch AI measured 0.878 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity