GLM 4.6 API pricing
Updated
Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for GLM 4.6 is Venice at USD 0.43 per 1M input tokens and USD 1.75 per 1M output tokens. The median across 6 standard prices is USD 0.55 / USD 2.10. Z.ai's own API charges USD 0.60 / USD 2.20.
What does Z.ai charge for GLM 4.6?
- Input
- USD 0.60
- Cached input
- USD 0.11
- Output
- USD 2.20
- Blended 3:1
- USD 1
USD per 1M tokens on Z.ai, model GLM-4.6, standard tier. Source, checked 2026-11-14.
Is a host cheaper than Z.ai? Yes. Venice charges USD 0.43 input and USD 1.75 output per 1M tokens, 24% below Z.ai's own USD 0.60 / USD 2.20 on the 3:1 blend.
GLM 4.6 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 32% above 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 | Venice cheapestzai-org-glm-4.6Notes and source quote“| GLM 4.6 | `zai-org-glm-4.6` | $0.43 | $1.75 | $0.08 | — | Private |” | USD 0.43 | USD 0.08 | USD 1.75 | USD 0.76 | 198,000 | FP4 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | DeepInfrazai-org/GLM-4.6Notes and source quote“$0.50 in $2.00 out $0.10 cached / 1M tokens” | USD 0.50 | USD 0.10 | USD 2 | USD 0.875 | 202,752 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | GMI Cloudzai-org/GLM-4.6Notes and source quoteNo cache-read price published. “Price (per 1M tokens) Input $0.60 Output $2.00” | USD 0.60 | not published | USD 2 | USD 0.95 | 204,800 | BF16 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 4 | Featherlesszai-org/GLM-4.6Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.55 / CACHED $0.11 / OUTPUT $2.2” | USD 0.55 | USD 0.11 | USD 2.20 | USD 0.9625 | 202,752 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 5 | Novita AIzai-org/glm-4.6Notes and source quote“GLM 4.6 200K $0.55 /Mt · Cache Read $0.11 /Mt $2.2 /Mt” | USD 0.55 | USD 0.11 | USD 2.20 | USD 0.9625 | 204,800 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 6 | Z.ai makerGLM-4.6Notes and source quote“| GLM-4.6 | $0.6 | $0.11 | Limited-time Free | $2.2 |” | USD 0.60 | USD 0.11 | USD 2.20 | USD 1 | not stated | not stated | Z.ai page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotzai-org/GLM-4.6Notes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.40 $1.60 $0.08” | USD 0.40 | USD 0.08 | USD 1.60 | USD 0.70 | 202,752 | FP4 | DeepInfra 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.
- Other tiers (flex / spot): 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 4.6 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) |
|---|---|---|---|
| Venice | USD 51.30 | USD 104.25 | USD 396.00 |
| DeepInfra | USD 59.40 | USD 121.20 | USD 468.00 |
| GMI Cloud | USD 90.00 | USD 174.00 | USD 1,260 |
| Featherless | USD 65.34 | USD 133.32 | USD 514.80 |
| Novita AI | USD 65.34 | USD 133.32 | USD 514.80 |
| Z.ai (maker) | USD 67.14 | USD 141.72 | USD 528.30 |
For the support chatbot, the cheapest price (Venice, USD 51.30 a month) saves USD 14.04 against the median (USD 65.34). For the coding agent the gap is USD 118.80 a month (23% lower).
Which GLM 4.6 provider is cheapest for your traffic?
Venice has the lowest input price (USD 0.43) and the lowest output price (USD 1.75), 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 |
|---|---|---|---|
| Venice | USD 0.76 cheapest | USD 0.6288 cheapest | USD 0.5237 cheapest |
| DeepInfra | USD 0.875 | USD 0.725 | USD 0.605 |
| GMI Cloud (no cache price) | USD 0.95 | USD 0.95 | USD 0.95 |
| Featherless | USD 0.9625 | USD 0.7975 | USD 0.6655 |
| Novita AI | USD 0.9625 | USD 0.7975 | USD 0.6655 |
| Z.ai (maker) | USD 1 | USD 0.8163 | USD 0.6693 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. 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.
5 of 6 providers publish a cached-input price below the input price: Venice (81% off), DeepInfra (80% off), Featherless (80% off), Novita AI (80% off), Z.ai (82% off). GMI Cloud publishes none, so cached tokens there bill at the input price.
Context windows differ: 204,800 tokens at GMI Cloud and Novita AI; 202,752 tokens at DeepInfra and Featherless; 198,000 tokens at Venice. Z.ai does not state one. The cheapest row is not always the one that fits a long prompt.
Estimate your own bill
- LLM API cost calculator with GLM 4.6 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 4.6 compare with other Z.ai models?
The Z.ai models whose cheapest standard price is closest to GLM 4.6's (USD 0.76 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| GLM 4.7 | USD 0.40 | USD 1.75 | 204,800 | 8 |
| GLM 5.2 | USD 0.5625 | USD 1.80 | 1,048,576 | 19 |
| GLM 4.5V | USD 0.60 | USD 1.80 | 65,536 | 2 |
| GLM 5 | USD 0.60 | USD 1.92 | 204,800 | 10 |
| GLM 5.3 FlashX | USD 0.37 | USD 1.25 | 1,048,576 | 2 |
| GLM-4.5-FP8 | USD 0.60 | USD 2.20 | 131,072 | 2 |
Priced closest from other makers: Mistral Large 3 (Mistral AI, USD 0.75) · Qwen2.5 Coder 32B Instruct (Qwen, USD 0.745) · Kimi K2.6 (Moonshot AI, USD 0.7425).
Compare GLM 4.6 with
- GLM 4.7 vs GLM 4.6: API price side by side
- GLM 4.6 vs GLM-4.5-FP8: API price side by side
Also compared: vs GLM 4.7 · vs GLM-4.5-FP8.
Every GLM 4.6 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 4.6 API cost per token?
From USD 0.43 per 1M input tokens (USD 0.00000043 per token) and USD 1.75 per 1M output tokens (USD 0.00000175 per token) at the lowest standard prices we found. The median of 6 standard prices is USD 0.55 input and USD 2.10 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 4.6?
Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Venice, ranked on a blend of 3 input tokens to 1 output token (USD 0.76 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is GLM 4.6 cheaper from a host than from Z.ai?
Yes. Venice charges USD 0.43 input and USD 1.75 output per 1M tokens, 24% below Z.ai's own USD 0.60 / USD 2.20 on the 3:1 blend.
Does GLM 4.6 have cached input pricing?
5 of 6 standard prices include one. The lowest is USD 0.08 per 1M at Venice; the median is USD 0.11. Providers without one bill cached input at the input price. What cached input means.
What is the GLM 4.6 context window?
Up to 204,800 tokens. 3 standard prices come with less, down to 198,000 tokens (Venice, DeepInfra and Featherless). 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 4.6?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 396.00 a month at Venice, USD 514.80 at the median price and USD 1,260 at GMI Cloud. Try your own numbers.
Is there a batch, flex or priority price for GLM 4.6?
Yes: flex / spot from DeepInfra at USD 0.40 / USD 1.60 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 4.6 free to use through an API?
No provider in our data lists a free price for GLM 4.6 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.