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-5.3 pricing and specs
GLM-5.3 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: Z.ai lists cached input storage as limited-time free, so no cache write price is billed. Text-only input. The release date is not listed because no primary page read on 2026-10-09 states the API launch date. Gateway routes for this model vary by provider and do not match the first-party price.
Specs
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Provider
- Z.ai
- API model id
glm-5.3- Vercel AI Gateway id
zai/glm-5.3- Weights
- Open weights
- License
- GLM-5.3 license (Hugging Face license tag: other)
- Weights download
- huggingface.co
What GLM-5.3 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
| Model | Input / 1M | Output / 1M |
|---|---|---|
| GLM-5.3 (this page) | $1.40 | $4.40 |
| Claude Haiku 5.5Anthropic | $0.10 | $0.50 |
| Claude Sonnet 5.5Anthropic | $2 | $10 |
| Claude Opus 5.5Anthropic | $4 | $20 |
| Claude Fable 5.1Anthropic | $10 | $50 |
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.
- ZCode Developer Guide 2026: Z.ai's Agentic IDE for GLM-5.3ZCode is Z.ai's free desktop agentic development environment tuned for GLM-5.3. Setup, Goal Mode, pricing, and how model connections work.
- Codex Custom Model Providers: GLM-5.3, Mistral and OllamaCodex only speaks the Responses API now. Tested config.toml blocks for GLM-5.3, Mistral Large 4 through a gateway, local Ollama and an internal proxy.
- 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.
FAQ
How much does GLM-5.3 cost per million tokens?
GLM-5.3 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 9, 2026. Per 1M tokens, cache reads cost $0.26.
What is GLM-5.3's context window?
GLM-5.3 has a 1,000,000-token context window and returns up to 128,000 output tokens per response.
Are GLM-5.3's weights open?
Yes. GLM-5.3's weights are published at https://huggingface.co/zai-org/GLM-5.3 under the GLM-5.3 license (Hugging Face license tag: other).
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.