GLM 5.2 API pricing
Updated
The cheapest standard price for GLM 5.2 is DeepInfra (promotional) at USD 0.5625 per 1M input tokens and USD 1.80 per 1M output tokens. The median across 19 standard prices is USD 1.40 / USD 4.40. Z.ai's own API charges USD 1.40 / USD 4.40. Every price is read from the provider's own pricing page, checked 2026-11-15.
What does Z.ai charge for GLM 5.2?
- Input
- USD 1.40
- Cached input
- USD 0.26
- Output
- USD 4.40
- Blended 3:1
- USD 2.15
USD per 1M tokens on Z.ai, model GLM-5.2, standard tier. Source, checked 2026-11-14.
Is a host cheaper than Z.ai? Yes. DeepInfra charges USD 0.5625 input and USD 1.80 output per 1M tokens, 59% below Z.ai's own USD 1.40 / USD 4.40 on the 3:1 blend (a promotional price).
GLM 5.2 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 2.7× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepInfra cheapest promozai-org/GLM-5.2Notes and source quotePromotional price, 25% off list (list 0.75 in / 2.4 out). “$0.563 in $1.80 out $0.105 cached / 1M tokens” | USD 0.5625 | USD 0.105 | USD 1.80 | USD 0.8719 | 1,048,576 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | CoreWeave Forgezai-org/GLM-5.2Notes and source quote“Z.AI GLM 5.2 $0.62 $2.42 $0.14” | USD 0.62 | USD 0.14 | USD 2.42 | USD 1.07 | 1,048,576 | not stated | CoreWeave Forge page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | Chuteszai-org/GLM-5.2-TEENotes and source quoteRuns on confidential TEE compute. “GLM-5.2 zai-org/GLM-5.2-TEE $0.125 per 1M tokens $1.25 per 1M tokens $3.95 per 1M tokens 1.0M” | USD 1.25 | USD 0.125 | USD 3.95 | USD 1.925 | 1,048,576 | FP4 | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| 4 | SiliconFlowNotes and source quoteContext shown as 1049K. “GLM-5.2 1049K $1.302 $0.26 $4.092” | USD 1.302 | USD 0.26 | USD 4.092 | USD 1.999 | 1,048,576 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 5 | Z.ai makerGLM-5.2Notes and source quote“| GLM-5.2 | $1.4 | $0.26 | Limited-time Free | $4.4 |” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | not stated | not stated | Z.ai page checked 2026-11-14 re-checked 2026-11-16 |
| 6 | Alibaba Cloudglm-5.2Notes and source quoteInternational (Singapore) deployment. Deployed by Alibaba Cloud Model Studio. A Zhipu-deployed variant, ZHIPU/GLM-5.2, is listed at the same price. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope. “glm-5.2 International Non-Thinking and Thinking modes flat-rate pricing $1.400 $4.400” | USD 1.40 | USD 0.28 | USD 4.40 | USD 2.15 | not stated | not stated | Alibaba Cloud page checked 2026-11-14 re-checked 2026-11-16 |
| 7 | Baiduglm-5.2Notes and source quote“GLM-5.2 GLM-5.2 Inference Service Input 1.4 $/M tokens Cache Hit 0.26 $/M tokens Output 4.4 $/M tokens” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | 500,000 | not stated | Baidu page checked 2026-11-15 re-checked 2026-11-16 |
| 8 | Basetenzai-org/GLM-5.2Notes and source quote“GLM-5.2 $1.40 $0.14 $4.40” | USD 1.40 | USD 0.14 | USD 4.40 | USD 2.15 | not stated | not stated | Baseten page checked 2026-11-14 re-checked 2026-11-16 |
| 9 | Cloudflare Workers AI@cf/zai-org/glm-5.2Notes and source quoteCloudflare publishes this USD per-token price alongside the neuron price. “@cf/zai-org/glm-5.2 $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | not stated | not stated | Cloudflare Workers AI page checked 2026-11-14 re-checked 2026-11-16 |
| 10 | DigitalOceanNotes and source quoteDigitalOcean-hosted. “GLM-5.2 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.40$4.40$0.21” | USD 1.40 | USD 0.21 | USD 4.40 | USD 2.15 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 11 | Featherlesszai-org/GLM-5.2Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $1.4 / CACHED $0.15 / OUTPUT $4.4” | USD 1.40 | USD 0.15 | USD 4.40 | USD 2.15 | 262,144 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 12 | FriendliAIzai-org/GLM-5.2Notes and source quote“Input $1.4 / 1M tokens Cached Input $0.26 / 1M tokens Output $4.4 / 1M tokens” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | 1,048,576 | not stated | FriendliAI page checked 2026-11-15 re-checked 2026-11-16 |
| 13 | GMI Cloudzai-org/GLM-5.2-FP8Notes and source quote“Price (per 1M tokens) Input $1.40 Output $4.40 Cache Read $0.26 Cache Write -” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | 1,048,576 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 14 | Google Vertex AIglm-5.2Notes and source quote“GLM-5.2 Input $1.40 … Output $4.40 … Cached Input: $0.14” | USD 1.40 | USD 0.14 | USD 4.40 | USD 2.15 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| 15 | Novita AIzai-org/glm-5.2Notes and source quote“GLM 5.2 1M $1.4 /Mt · Cache Read $0.26 /Mt $4.4 /Mt” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | 1,048,576 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 16 | ParasailNotes and source quote“GLM-5.2 $1.40 $4.40 $0.26” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | not stated | not stated | Parasail page checked 2026-11-14 re-checked 2026-11-16 |
| 17 | Together AINotes and source quote“GLM-5.2 $1.40 $0.26 (cached) $4.40” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | not stated | not stated | Together AI page checked 2026-11-14 re-checked 2026-11-16 |
| 18 | Venicezai-org-glm-5-2Notes and source quote“| GLM 5.2 | `zai-org-glm-5-2` | $1.40 | $4.40 | $0.26 | — | Private |” | USD 1.40 | USD 0.26 | USD 4.40 | USD 2.15 | 1,000,000 | FP8 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 19 | Microsoft AzureNotes and source quoteFoundry Models serverless, served by Fireworks on Azure, Data Zone deployment. “FW GLM 5.2 Data Zone Input: $1.54/1M Tokens | Cached Input: $0.15/1M Tokens | Output: $4.84/1M Tokens” | USD 1.54 | USD 0.15 | USD 4.84 | USD 2.365 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spot promozai-org/GLM-5.2Notes and source quoteFlex service tier (0.8× standard). Promotional price, 25% off list (list 0.75 in / 2.4 out). “Flex (0.8×) $0.45 $1.44 $0.084” | USD 0.45 | USD 0.084 | USD 1.44 | USD 0.6975 | 1,048,576 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra priority promozai-org/GLM-5.2Notes and source quotePriority service tier (1.5× standard). Promotional price, 25% off list (list 0.75 in / 2.4 out). “Priority (1.5×) $0.8438 $2.70 $0.1575” | USD 0.8438 | USD 0.1575 | USD 2.70 | USD 1.308 | 1,048,576 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | Baseten fastzai-org/GLM-5.2-FastNotes and source quote“GLM-5.2 Fast $2.10 $0.21 $6.60” | USD 2.10 | USD 0.21 | USD 6.60 | USD 3.225 | not stated | not stated | Baseten page checked 2026-11-14 re-checked 2026-11-16 |
| — | Microsoft Azure fastNotes and source quoteFoundry Models serverless, served by Fireworks on Azure, Data Zone deployment. “FW GLM 5.2 Fast Data Zone Input: $2.31/1M Tokens | Cached Input: $0.231/1M Tokens | Output: $7.26/1M Tokens” | USD 2.31 | USD 0.231 | USD 7.26 | USD 3.547 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | Baidu fastglm-5.2-fastNotes and source quoteGLM-5.2-Fast, the fast version of GLM-5.2. “GLM-5.2-Fast GLM-5.2-Fast Inference Service Input 2.25 $/M tokens Cache Hit 0.56 $/M tokens Output 7.88 $/M tokens” | USD 2.25 | USD 0.56 | USD 7.88 | USD 3.657 | 1,048,576 | not stated | Baidu page checked 2026-11-15 re-checked 2026-11-16 |
| — | Chutes fastzai-org/GLM-5.2-FastNotes and source quoteFast variant, model ID zai-org/GLM-5.2-Fast. “GLM-5.2-Fast zai-org/GLM-5.2-Fast $0.49 per 1M tokens $2.45 per 1M tokens $7.70 per 1M tokens 1.0M” | USD 2.45 | USD 0.49 | USD 7.70 | USD 3.763 | 1,048,576 | not stated | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| — | Alibaba Cloud fastglm-5.2-fast-previewNotes and source quoteInternational (Singapore) deployment. Fast mode (Prime), Singapore tab of the Fast mode page; the model pricing page lists the same 2.8 input, 8.8 output. “glm-5.2-fast-preview $2.800 $8.800 $0.560” | USD 2.80 | USD 0.56 | USD 8.80 | USD 4.30 | not stated | not stated | Alibaba Cloud page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Promo: the provider's page describes this price as promotional or discounted (DeepInfra). It ranks as published, but can end without notice; the row's notes give the list price or end date where the page states one.
- Other tiers (flex / spot, priority and fast): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does GLM 5.2 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.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| DeepInfra (promo) | USD 58.32 | USD 129.06 | USD 474.53 |
| CoreWeave Forge | USD 73.44 | USD 150.54 | USD 599.40 |
| Chutes | USD 122.85 | USD 278.25 | USD 884.25 |
| SiliconFlow | USD 134.57 | USD 298.84 | USD 1,118 |
| Z.ai (maker) | USD 143.64 | USD 319.92 | USD 1,172 |
| Alibaba Cloud | USD 144.72 | USD 321.36 | USD 1,202 |
| Baidu | USD 143.64 | USD 319.92 | USD 1,172 |
| Baseten | USD 137.16 | USD 311.28 | USD 988.20 |
| Cloudflare Workers AI | USD 143.64 | USD 319.92 | USD 1,172 |
| DigitalOcean | USD 140.94 | USD 316.32 | USD 1,095 |
| Featherless | USD 137.70 | USD 312.00 | USD 1,004 |
| FriendliAI | USD 143.64 | USD 319.92 | USD 1,172 |
| GMI Cloud | USD 143.64 | USD 319.92 | USD 1,172 |
| Google Vertex AI | USD 137.16 | USD 311.28 | USD 988.20 |
| Novita AI | USD 143.64 | USD 319.92 | USD 1,172 |
| Parasail | USD 143.64 | USD 319.92 | USD 1,172 |
| Together AI | USD 143.64 | USD 319.92 | USD 1,172 |
| Venice | USD 143.64 | USD 319.92 | USD 1,172 |
| Microsoft Azure | USD 150.66 | USD 342.12 | USD 1,081 |
For the support chatbot, the cheapest price (DeepInfra, USD 58.32 a month) saves USD 85.32 against the median (USD 143.64). For the coding agent the gap is USD 697.28 a month (60% lower).
Which GLM 5.2 provider is cheapest for your traffic?
DeepInfra has the lowest input price (USD 0.5625) and the lowest output price (USD 1.80), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| DeepInfra | USD 0.8719 cheapest | USD 0.7003 cheapest | USD 0.5631 cheapest |
| CoreWeave Forge | USD 1.07 | USD 0.89 | USD 0.746 |
| Chutes | USD 1.925 | USD 1.503 | USD 1.166 |
| SiliconFlow | USD 1.999 | USD 1.609 | USD 1.296 |
| Z.ai (maker) | USD 2.15 | USD 1.723 | USD 1.381 |
| Alibaba Cloud | USD 2.15 | USD 1.73 | USD 1.394 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 13 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.
All 19 providers publish a cached-input price below the input price: DeepInfra (81% off), CoreWeave Forge (77% off), Chutes (90% off), SiliconFlow (80% off), Z.ai (81% off) and 14 more.
Context windows differ: 1,048,576 tokens at DeepInfra, CoreWeave Forge, Chutes and 4 more; 1,000,000 tokens at Venice; 500,000 tokens at Baidu; 262,144 tokens at Featherless. Z.ai, Alibaba Cloud, Baseten, Cloudflare Workers AI, DigitalOcean and 4 more do not state one. The cheapest row is not always the one that fits a long prompt.
What does GLM 5.2 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 5.2:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.135 | CoreWeave Forge |
| Arabic MSA | USD 0.256 | CoreWeave Forge |
| Hindi | USD 0.555 | CoreWeave Forge |
| Chinese | USD 0.368 | CoreWeave Forge |
| Code | USD 0.158 | CoreWeave Forge |
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.
| Benchmark | Result | Setting or note | Source |
|---|---|---|---|
| GPQA-Diamond | 91.2 | not stated | Z.ai model card, checked 2026-11-16 |
| SWE-bench Pro | 62.1 | not stated | Z.ai model card, checked 2026-11-16 |
| Terminal Bench 2.1 (Terminus-2) | 81.0 | not stated | Z.ai model card, checked 2026-11-16 |
| MCP-Atlas (Public Set) | 76.8 | not stated | Z.ai model card, checked 2026-11-16 |
| GPQA Diamond | 0.919 | Max reasoning setting; Epoch run glm-5.2_max, mean score on a 0 to 1 scale | Epoch 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
- LLM API cost calculator with GLM 5.2 preloaded: your traffic and cache rate, against any of 428 models.
- GLM token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does GLM 5.2 compare with other Z.ai models?
The Z.ai models whose cheapest standard price is closest to GLM 5.2's (USD 0.8719 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| GLM 4.5V | USD 0.60 | USD 1.80 | 65,536 | 2 |
| GLM 5 | USD 0.60 | USD 1.92 | 204,800 | 10 |
| GLM-4.5-FP8 | USD 0.60 | USD 2.20 | 131,072 | 2 |
| GLM 4.6 | USD 0.43 | USD 1.75 | 204,800 | 6 |
| GLM 4.7 | USD 0.40 | USD 1.75 | 204,800 | 8 |
| GLM 5.3 | USD 0.5625 | USD 2.50 | 1,048,576 | 24 |
Priced closest from other makers: Gemini 2.5 Flash (Google, USD 0.85) · Gemini 3.5 Flash-Lite (Google, USD 0.85) · Kimi K2.5 (Moonshot AI, USD 0.90).
Compare GLM 5.2 with
- GLM 5.3 vs GLM 5.2: API price side by side
- GLM 5.2 vs GLM 5.1: API price side by side
Also compared: vs GLM 5.3 · vs GLM 5.1.
Every GLM 5.2 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 5.2 API cost per token?
From USD 0.5625 per 1M input tokens (USD 0.0000005625 per token) and USD 1.80 per 1M output tokens (USD 0.0000018 per token) at the cheapest standard price. The median of 19 standard prices is USD 1.40 input and USD 4.40 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 5.2?
DeepInfra (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 0.8719 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 5.2 cheaper from a host than from Z.ai?
Yes. DeepInfra charges USD 0.5625 input and USD 1.80 output per 1M tokens, 59% below Z.ai's own USD 1.40 / USD 4.40 on the 3:1 blend (a promotional price).
Does GLM 5.2 have cached input pricing?
All 19 standard prices include one. The lowest is USD 0.105 per 1M at DeepInfra; the median is USD 0.26. Providers without one bill cached input at the input price. What cached input means.
What is the GLM 5.2 context window?
Up to 1,048,576 tokens. 3 standard prices come with less, down to 262,144 tokens (Featherless, Baidu and Venice). 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 5.2?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 474.53 a month at DeepInfra, USD 1,172 at the median price and USD 1,202 at Alibaba Cloud. Try your own numbers.
Is there a batch, flex or priority price for GLM 5.2?
Yes: flex / spot from DeepInfra at USD 0.45 / USD 1.44; priority from DeepInfra at USD 0.8438 / USD 2.70; fast from Baseten at USD 2.10 / USD 6.60 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is GLM 5.2 free to use through an API?
No provider in our data lists a free price for GLM 5.2 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 5.2 score on benchmarks?
As published, the Z.ai model card reports 91.2 on GPQA-Diamond and 62.1 on SWE-bench Pro; Epoch AI measured 0.919 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
Sources
- Alibaba Cloud: pricing (checked 2026-11-14)
- Alibaba Cloud: pricing (checked 2026-11-14)
- Microsoft Azure: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- Baseten: pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- DigitalOcean: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- FriendliAI: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- Google Vertex AI: pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- Parasail: pricing (checked 2026-11-14)
- SiliconFlow: pricing (checked 2026-11-14)
- Together AI: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)
- Z.ai: own API pricing (checked 2026-11-14)