← 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 the tbench.ai Terminal-Bench 4.0 leaderboard, 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: tbench.ai Terminal-Bench 4.0 leaderboard. How we compute this

Run GLM 5.3 in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a 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.

GLM 5.3 benchmarks, speed and latency

Artificial AnalysisValueRank
Intelligence Index10 evaluations, 0 to 1004512 of 48
Terminal-Bench 4.0agentic coding in a terminal41.9%10 of 39
Output speedmedian69 tokens/s31 of 44
Time to first answer tokenincludes thinking time32 s18 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: GLM-5.3 (Max), speed on Z AI. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

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)

Leaderboards

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 has the highest open-weight score on the tbench.ai Terminal-Bench 4.0 leaderboard (41.8%), scores 41.9% in Artificial Analysis's own Terminal-Bench 4.0 run and 45 on the Artificial Analysis Intelligence Index, and 95.6 on Scale's SWE-Bench Pro V2. Reasoning is always on, and it outputs about 69 tokens per second. Cache reads cost $0.26 per million, so it costs slightly more per request than Claude Sonnet 5.5 in our measurements ($0.057 vs $0.053). Z.AI also sells smaller Flash and FlashX variants.

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

Agents that support GLM 5.3

Coding agents that need open weights and strong agentic scores.

Setting it up? GLM 5.3: model ID, providers and agent config →

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.
How fast is GLM 5.3?
Artificial Analysis measures GLM-5.3 (Max) at 69 output tokens per second, with 32 seconds to the first answer token, thinking time included, on Z AI's API. Source: Artificial Analysis (artificialanalysis.ai).
Is GLM 5.3 good for AI agents?
Coding agents that need open weights and strong agentic scores. On our scoring, which is calibrated to public benchmarks, it rates 8.2/10 for agentic ability and 8.4/10 for output quality. Top open-weight score on the tbench.ai Terminal-Bench 4.0 leaderboard (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 or run it through a hosted provider such as OpenRouter. Check the license before commercial use.
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; Cache reads at $0.26 per million make it cost slightly more per request than Sonnet 5.5; OpenRouter provider prices vary widely from Z.AI's list price. It's strongest for coding agents that need open weights and strong agentic scores.

GLM 5.3 compared

All 21 GLM 5.3 comparisons

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

Every model on this page runs on Standard Compute

Standard Compute

Current frontier models Claude Fable 5.1 · GPT-6 Astra

More intelligence
per dollar.

Each step goes to the cheapest model that can do it, on providers we vet for price, uptime and speed, with automatic fallback when one fails.

Compliance
Opt-in rules keep a company, team or key on European or US providers
Privacy
We don’t train on your prompts or store them

Fixed monthly plans from $19 · cancel anytime

7-day fair refund Free trial, no card Billing by Stripe4,200+ agent users