Z.ai: GLM-5.3
GLM-5.3 is a reasoning model from Z.ai released on Aug 14, 2026. It reads text and writes text, with a 1M token context window and up to 131K tokens per reply.
Show moreShow less
It costs $1.40 per million input tokens and $4.40 per million output tokens. Cached input bills at $0.26, 81% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
68 providers serve it, including Deep Infra, Friendli and Cloudflare Workers AI. The lowest input price is $0.90 per million tokens at Deep Infra.
On the Artificial Analysis Intelligence Index it scores 44.8, which places it in the top ten, at number 10, among the 43 models I track with independent scores.
- Modalities
- In / out price
- $1.40 / $4.40 per 1M
- Context
- 1M
- Max output
- 131K
- Released
- Aug 14, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
GLM-5.3 pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $1.40 / 1M tokens | |
|---|---|---|
| Output | $4.40 / 1M tokens | |
| Cached input (read) | $0.26 / 1M tokens | 81% off input |
| Cache write | $0 / 1M tokens |
GLM-5.3 providers
68 providers serve it, including Deep Infra, Friendli and Cloudflare Workers AI. The lowest input price is $0.90 per million tokens at Deep Infra. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Zhipu AI First party | $1.40 | $4.40 | $0.26 | 1M | 131K |
| Deep Infra | $0.90 | $4 | $0.20 | 1.05M | 131K |
| Friendli | $1.26 | $3.96 | $0.234 | 1.05M | 131K |
| Cloudflare Workers AI | $1.40 | $4.40 | $0.26 | 1.05M | 1.05M |
| Fireworks AI | $1.40 | $4.40 | $0.26 | 1.05M | 262K |
| Hugging Face | $1.40 | $4.40 | – | 1.05M | 131K |
| Mistral | $1.40 | $4.40 | $0.14 | 1.05M | 131K |
| Nebius Token Factory | $1.40 | $4.40 | $1.40 | 1.02M | 1.02M |
| Novita AI | $1.40 | $4.40 | $0.26 | 1.05M | 131K |
| SiliconFlow | $1.40 | $4.40 | $0.26 | 1.05M | 262K |
| Together AI | $1.40 | $4.40 | $0.26 | 1.05M | 262K |
| Vercel AI Gateway | $1.40 | $4.40 | $0.14 | 1M | 1M |
Showing 12 of 68 providers: the lab first, then the major clouds, then the cheapest resellers.
What GLM-5.3 costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by Z.ai. Each links to its source and shows the date I checked it.
A composite of 10 independent evaluations (agents 30%, coding 20%, scientific reasoning 20%, general 30%), run by Artificial Analysis on each model, version 4.3.2.
Artificial Analysis, checked Oct 10, 2026
Human preference: people compare two anonymous answers and pick the better one. Ratings from the Text Arena overall board, style control on.
Arena (formerly LMArena), checked Oct 10, 2026
Agentic coding in a real terminal: can the model, driving an agent harness, finish multi step software and ops tasks. Resolution rate.
Terminal-Bench, checked Oct 10, 2026
Expert level questions across many fields, no tools allowed. The Diamond set is 1,000 questions. Few models are on it yet.
Scale Labs, checked Oct 10, 2026
Median output tokens per second measured by Artificial Analysis on the provider API, for the same model setting as its index score.
Artificial Analysis, checked Oct 10, 2026
Benchmarks Z.ai reports (9)
- terminal-bench-2.1 (Terminal Bench 2.1)88.2%
- terminal-bench-3.0 (Terminal Bench 3.0, Claude Code 2.1.207 harness, reasoning effort max, 400K context, avg@3)28.3%
- deepswe-v1.1 (DeepSWE (v1.1), mini-swe-agent harness, 400K context)66.9%
- hle-with-tools (HLE w/ Tools, max generation 163,840 tokens, 300K context with context management, GPT-5.6-luna (medium) judge)62.5%
- cybergym (CyberGym, Claude Code 2.1.207, single-run Pass@1 over 1,507 tasks)84.5%
- toolathlon-verified (Toolathlon Verified)73%
- automationbench (AutomationBench (v1.0.6))48.2%
- agents-last-exam (Agents' Last Exam (ALE-CLI), Claude Code harness, reasoning effort max)28.5%
- nl2repo-bench (NL2Repo, 1M context)58
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call GLM-5.3 through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to GLM-5.3
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 48.1
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 13 providers.
by metaSep 2, 20261.05M context$1.25/M input tokens$4.25/M output tokens13 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 15 providers.
by metaAug 5, 2026$1.25/M input tokens$4.25/M output tokens15 providers
- 200K context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 36 providers.
by anthropicOct 1, 2025$1/M input tokens$5/M output tokens36 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 29 providers.
by x-aiApr 17, 2026$1.25/M input tokens$2.50/M output tokens29 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 11 providers.
by x-aiMar 9, 2026$1.25/M input tokens$2.50/M output tokens11 providers
- Index 40.9
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 24 providers.
by googleSep 2, 20261.05M context$0.75/M input tokens$3.75/M output tokens24 providers
More from Z.ai
- 1.05M context
Reads text and images. Tool calling, reasoning.
by z-aiOct 5, 2026$0.15/M input tokens$0.50/M output tokens
- 1.05M context
Reads text and images. Tool calling, reasoning.
by z-aiOct 5, 2026$0.15/M input tokens$0.50/M output tokens
- 1.05M context
Reads text. Tool calling, reasoning.
by z-aiSep 26, 2026$1.25/M input tokens$2.25/M output tokens
- 1M context
Reads text. Tool calling, reasoning.
by z-aiSep 23, 2026$2.80/M input tokens$8.80/M output tokens
- 1.05M context
Reads text and images. Tool calling, reasoning.
by z-aiSep 19, 2026$0.15/M input tokens$0.50/M output tokens
- 1.05M context
Reads text, images and video. Tool calling, reasoning.
by z-aiSep 18, 2026$0.37/M input tokens$1.25/M output tokens
GLM-5.3 questions
How much does the GLM-5.3 API cost?
$1.40 per million input tokens and $4.40 per million output tokens, with cached input at $0.26. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of GLM-5.3?
1,000,000 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve GLM-5.3?
68 providers serve it, including Deep Infra, Friendli and Cloudflare Workers AI. The lowest input price is $0.90 per million tokens at Deep Infra. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does GLM-5.3 support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is GLM-5.3 open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was GLM-5.3 released?
Aug 14, 2026.
How good is GLM-5.3 compared with other models?
It scores 44.8 on the Artificial Analysis Intelligence Index and 1478 on the Arena text leaderboard. Benchmarks are a shortlist, not a verdict: test the top two or three candidates on your own tasks before you commit.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on GLM-5.3?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting