GLM-4.7
Z.AI legacyGLM-4.7 by Z.AI: $0.6/M cache-miss input, $2.20/M output tokens. Cached input: $0.11/M. 200K context, 128K max output. Function Calling & JSON Mode. Price verified 2026-11-18.
Input Price
$0.6
cache miss / 1M tokens
Cached Input
$0.11
per 1M tokens
Output Price
$2.20
per 1M tokens
Context Window
200K
tokens
China (CNY) price: ¥3/M input, ¥0.6/M cached input, ¥14/M output (Mainland China, input <32K, output ≥0.2K) on Z.AI's official mainland price list. Details
GLM-4.7 official China pricing (CNY)
Mainland China list price from Z.AI, in CNY per 1M tokens. Verified 2026-11-18. The USD prices above are Z.AI's international list price, not a currency conversion.
| Rate | Cached input | Input | Output |
|---|---|---|---|
| Mainland China, input <32K, output ≥0.2K | ¥0.6 | ¥3 | ¥14 |
GLM-4.7 price history
No price changes recorded for GLM-4.7 in our AI API price change log (earliest entry: 2026-05-27). Current rates last verified against the official Z.AI pricing page on 2026-11-18. See all AI API price changes
Cheaper ways to use GLM-4.7
Current free credits and discounts that apply to Z.AI models.
- 🧠智谱 BigModelFree Credits— 20M free tokens for new sign-ups; GLM-4.7-Flash and GLM-4-Flash-250414 are free to call
- 🌋火山方舟(豆包)Free Tier— Up to 5M free inference tokens per day on Doubao-Seed-2.1-pro (check the console for the exact allowance)
- 💧硅基流动 SiliconFlowFree Credits— ¥16 voucher after real-name verification; referrer and new user each get ¥16; several small models are freeends 2026-12-31
Specifications
| Provider | Z.AI |
| Model ID | glm-4.7 |
| Input Price | $0.6 / 1M cache-miss tokens |
| Cached Input Price | $0.11 / 1M tokens |
| Output Price | $2.20 / 1M tokens |
| Context Window | 200K tokens |
| Max Output | 128K tokens |
| Capabilities | textfunction_callingstructured_output |
| Release Date | 2025-12-22 |
| Pricing Source | Official Z.AI pricing |
| Price Verified | 2026-11-18 |
| Notes | Coding and agentic GLM model from December 2025. Cached-input storage is free for a limited time. China pricing is tiered by input and output length (¥2/¥8 to ¥4/¥16). |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $0.42 | $5.04 |
| 50K | $2.10 | $25.20 |
| 100K | $4.20 | $50.40 |
| 500K | $21.00 | $252.00 |
| 1.0M | $42.00 | $504.00 |
How GLM-4.7 Pricing Compares
Standard cache-miss input / output prices per 1M tokens, compared with active, price-verified models priced in USD. Cached, batch and long-context rates are not included.
- Within Z.AI: 3 of 9 other active Z.AI models have a lower input price, and 3 have a lower output price.
- Similar context window: among the 19 active models with a 100K–400K token context window, GLM-4.7 ranks #10 from cheapest at a 50/50 input/output mix. Cheapest: GLM-4.7-Flash ($0.00/$0.00). Most expensive: Jamba Large 1.7 ($2.00/$8.00).
Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
GLM-4.7 Key Details
- Pricing: $0.6/M cache-miss input tokens, $0.11/M cached input tokens, $2.20/M output tokens
- Context window: 200K tokens — 81 of 90 active models we track have a larger window
- Max output: 128K tokens per response
- Capabilities: text, function_calling, structured_output
- Highlights: Coding and agentic GLM model from December 2025. Cached-input storage is free for a limited time. China pricing is tiered by input and output length (¥2/¥8 to ¥4/¥16).
- Released: 2025-12-22
Other Z.AI Models
Similar Price Range
Related Tools
FAQ
How much does GLM-4.7 cost?
GLM-4.7 costs $0.6 per million cache-miss input tokens and $2.20 per million output tokens. Cached input costs $0.11 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $5.10/month before cache-hit savings.
What is GLM-4.7's context window?
GLM-4.7 supports a context window of 200K tokens. This means your combined input prompt and output response can be up to 200K tokens. The maximum output per response is 128K tokens.
Is GLM-4.7 good for my use case?
GLM-4.7 supports text, function_calling, structured_output. We track pricing and limits, not output quality, so test it on your own prompts before committing. The price comparison above lists cheaper and pricier models with a similar context window, and the Pricing Calculator estimates your monthly cost across all of them.