One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.07 = $0.07
- Output0.1M x $0.40 = $0.04
$0.11per session
Z.ai - Closed weights
GLM-4.7-FlashX pricing and specs
GLM-4.7-FlashX is a closed-weights model from Z.ai that costs $0.07 per 1M input tokens and $0.40 per 1M output tokens on the first-party API, with a 200K-token context window.
Last verified from docs.z.ai. All sources
- Input / 1M
- $0.07
- Output / 1M
- $0.40
- Context
- 200K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.07 |
| Output | $0.40 |
| Cache read | $0.01 |
Note: Listed under 'Other Pricing' on the pricing page. The GLM-4.7 model page's FlashX tab gives 200K context and 128K max output and calls it 'Lightweight, High-Speed, and Affordable'. The release date is left blank because the release notes have no FlashX entry. weights is closed because no FlashX weights repo exists; the free GLM-4.7-Flash has weights at huggingface.co/zai-org/GLM-4.7-Flash. The model code is not in the OpenAPI enum read today, so API model id follows the docs' lowercase naming.
Specs
- Context window
- 200,000 tokens
- Max output
- 128,000 tokens
- Provider
- Z.ai
- API model id
glm-4.7-flashx- Vercel AI Gateway id
zai/glm-4.7-flashx- Weights
- Closed weights
What GLM-4.7-FlashX costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.07 = $1.40
- Output5M x $0.40 = $2.00
$3.40per day
$102.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.01 = $0.009
- Uncached input0.1M x $0.07 = $0.007
- Output0.1M x $0.40 = $0.04
$0.056per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| GLM-4.7-FlashX (this page) | $0.07 | $0.40 |
| Gemini 2.5 Flash-LiteGoogle | $0.10 | $0.40 |
| GPT-4.1 nanoOpenAI | $0.10 | $0.40 |
| GPT-5 nanoOpenAI | $0.05 | $0.40 |
| Jamba2 MiniAI21 Labs | $0.20 | $0.40 |
| GLM-5.3-FlashZ.ai | $0.15 | $0.50 |
| GLM-4-32B-0414-128KZ.ai | $0.10 | $0.10 |
| GLM-4.6VZ.ai | $0.30 | $0.90 |
| GLM-4.5-AirZ.ai | $0.20 | $1.10 |
| GLM-5.3-FlashXZ.ai | $0.37 | $1.25 |
| GLM-4.5Z.ai | $0.60 | $2.20 |
Related reading
- Anthropic's GLM-5.3 Cyber Report: The Numbers, the Backlash, and What Developers Should Take From ItAnthropic's GLM-5.3 cyber report: exploit numbers against Claude Mythos Preview, how its safeguards were stripped, the backlash, and the read for developers.
- GLM-5.3 Free and Cheap: Every Route and Price (October 2026)GLM-5.3 has no free hosted tier. Cheapest on October 9: Wafer via OpenRouter at $0.049/$3.39, Flash from $0.075/$0.25. Z.ai's promos ended October 7.
- Prime Agent: A Self-Improving Coding Harness Where Everything Is PythonPrime Agent is Prime Intellect's open-source coding harness with one tool, a persistent IPython kernel. How it works, its benchmarks, and Claude Code compared.
- Cloudflare Runs Kimi and GLM at Scale: FP8 KV Caches, INT4 Weights, and a Cache Safety NetCloudflare runs Kimi K2.6 and GLM 5.2 on Workers AI with FP8 KV caches, INT4 weights and a KV cache integrity check. What each technique buys on GPU fleets.
- Colibri: Run GLM 5.2 on a 32GB Laptop With Disk StreamingA solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.
- GLM 5.2 Matches Human Bookkeeper Accuracy on UK VAT Returns - With Some CaveatsGLM 5.2 UK VAT return benchmark: how the model handled 59 transactions with near-human bookkeeper accuracy, where it erred, and why HN focused on liability.
FAQ
How much does GLM-4.7-FlashX cost per million tokens?
GLM-4.7-FlashX costs $0.07 per 1M input tokens and $0.40 per 1M output tokens on Z.ai's first-party API, per docs.z.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.01.
What is GLM-4.7-FlashX's context window?
GLM-4.7-FlashX has a 200,000-token context window and returns up to 128,000 output tokens per response.
Are GLM-4.7-FlashX's weights open?
No. GLM-4.7-FlashX is a closed-weights model. You call it through Z.ai's API as glm-4.7-flashx or through Vercel AI Gateway as zai/glm-4.7-flashx.
Sources
Last verified from docs.z.ai.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.