Standard Compute
← All models
GLM 5.3 · Z.AI

What does GLM 5.3 cost to run in a coding agent?

GLM 5.3 costs about $0.057 per average coding-agent request on our measured traffic, at list prices of $1.40 per million input and $4.40 per million output tokens. It is the highest-scoring open-weight model on Terminal-Bench 4.0, at 41.8%.

List prices: Z.AI pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. Benchmark: Terminal-Bench 4.0 leaderboard. How we compute this

Run GLM 5.3 in your agent from $19/month

See plans

What GLM 5.3 costs per coding-agent request

Cost at list priceGLM 5.3
Prompt under 100K tokens50% of requests, 87% of input cached$0.026
Prompt of 100K to 272K39% of requests, 88% of input cached$0.070
Prompt over 272K tokens11% of requests, 86% of input cached$0.16
Average request$0.057
100 requests$5.72
Median session16 requests; a session ends after 10 idle minutes$0.71
A month of regular usemedian of 20 users active on 5+ days$92.16

Each logged request priced at the vendor's list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

What to watch for

Z.AI charges $0.26 per million for cache reads, 19% of its input price, where Anthropic and OpenAI charge 5 to 10%. Cache-heavy agent traffic therefore costs more than the list price suggests: GLM 5.3 came out 7% more expensive per request than Claude Sonnet 5.5 despite a 30% lower input price. Reasoning is always on, which adds output tokens.

Where GLM 5.3 sits on the Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index bar chart with GLM-5.3 (max) highlighted, from artificialanalysis.ai, October 13, 2026
Artificial Analysis Intelligence Index v4.3.2, GLM-5.3 (max) highlighted, downloaded October 13, 2026. Source: Artificial Analysis (artificialanalysis.ai)

About GLM 5.3

GLM 5.3 is Z.AI's flagship, a 753B mixture-of-experts model post-trained on the GLM 5.2 base, with a 1M-token context and 128K output. It reached the API on August 14, 2026 and its weights followed on August 29 under a custom GLM 5.3 license. It is the highest-scoring open-weight model on the Terminal-Bench 4.0 leaderboard (41.8%), scores 95.6 on Scale's SWE-Bench Pro V2 and 45 on the Artificial Analysis Intelligence Index. Reasoning is always on. Z.AI also sells smaller Flash and FlashX variants.

Sources: Z.AI docs · Hugging Face · Terminal-Bench 4.0 · SWE-Bench Pro V2

Agents that run GLM 5.3 well

Open-weight coding agents that need near-frontier agentic ability.

GLM 5.3 FAQ

How much does GLM 5.3 cost per coding-agent request?
$0.057 on average at list price, $5.72 per 100 requests, and $0.71 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at Z.AI's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.
Does GLM 5.3 charge more for long prompts?
No. GLM 5.3 bills the same rate per token up to its 1M-token context window.
Is GLM 5.3 good for AI agents?
Open-weight coding agents that need near-frontier agentic ability. On our editorial scoring it rates 9.4/10 for agentic ability and 9.3/10 for output quality. Top open-weight score on Terminal-Bench 4.0 (41.8%).
What is GLM 5.3's context window?
GLM 5.3 has a 1.0M-token context window — large enough to hold sizeable codebases or document sets in a single run. Z.AI is the maker.
Is GLM 5.3 open source?
Yes — GLM 5.3 ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of GLM 5.3?
The main trade-offs: Custom license with conditions for very large hosting providers; Reasoning cannot be turned off; OpenRouter provider prices vary widely from Z.AI's list price. It's strongest for open-weight coding agents that need near-frontier agentic ability.

GLM 5.3 compared

The agent matters as much as the model. Which agent gets the most out of GLM 5.3? →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Opus 5.5 · Claude Sonnet 5.5

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. The most intelligence per dollar. One flat bill.

Plans from $19/mo · cancel anytime · 7-day fair refund

7-day fair refund No credit card needed Billing by Stripe1,800+ agent users