One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $1.40 = $1.40
- Output0.1M x $4.40 = $0.44
$1.84per session
Z.ai - Open weights
GLM-5.2 pricing and specs
GLM-5.2 is an open-weights model from Z.ai that costs $1.40 per 1M input tokens and $4.40 per 1M output tokens on the first-party API, with a 1M-token context window.
Last verified from docs.z.ai. All sources
- Input / 1M
- $1.40
- Output / 1M
- $4.40
- Context
- 1M tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $1.40 |
| Output | $4.40 |
| Cache read | $0.26 |
Note: Same price as GLM-5.3, and GLM-5.3 uses the same base model. Text-only input. Cached input storage is limited-time free, so no cache write price is billed.
Specs
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Release date
- Provider
- Z.ai
- API model id
glm-5.2- Vercel AI Gateway id
zai/glm-5.2- Weights
- Open weights
- License
- MIT
- Weights download
- huggingface.co
What GLM-5.2 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 $1.40 = $28.00
- Output5M x $4.40 = $22.00
$50.00per day
$1,500.00 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 $0.26 = $0.234
- Uncached input0.1M x $1.40 = $0.14
- Output0.1M x $4.40 = $0.44
$0.814per session
Compare with
Compare
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
Related reading
- 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.
- 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.
- GLM 5.2 and the AI Margin Collapse ThesisGLM 5.2 and the AI margin collapse thesis: why open-weights models could squeeze frontier lab margins, where HN pushes back, and what it means for model choice.
- GLM 5.2 in 9 Minutes: The Open-Weight Rival to GPT-5.5GLM 5.2 in 9 minutes: a companion guide to the video on the open-weight GPT-5.5 rival, covering benchmarks, pricing and a live OpenCode demo.
- GLM 5.2 Outperforms Claude Code on Semgrep's IDOR Vulnerability BenchmarksGLM 5.2 vs Claude Code on Semgrep IDOR benchmarks: the open-weight model scored higher at about one-sixth the cost per finding. Setup, results and HN reactions.
FAQ
How much does GLM-5.2 cost per million tokens?
GLM-5.2 costs $1.40 per 1M input tokens and $4.40 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 $0.26.
What is GLM-5.2's context window?
GLM-5.2 has a 1,000,000-token context window and returns up to 128,000 output tokens per response.
Are GLM-5.2's weights open?
Yes. GLM-5.2's weights are published at https://huggingface.co/zai-org/GLM-5.2 under the MIT.
When was GLM-5.2 released?
Z.ai released GLM-5.2 on June 16, 2026.
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.