GLM 5.2 · Z.AI

What does GLM 5.2 cost to run in a coding agent?

GLM 5.2 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 scores 34 on the Artificial Analysis Intelligence Index, 25th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

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. How we compute this

A newer version is out. GLM 5.3 →

Run GLM 5.2 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 5.2 costs per coding-agent request

Cost at list price	GLM 5.2
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 5.2 benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	34	25 of 48
Terminal-Bench 4.0agentic coding in a terminal	1.0%	30 of 39
Output speedmedian	83 tokens/s	27 of 44
Time to first answer tokenincludes thinking time	27 s	16 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: GLM-5.2 (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.

About GLM 5.2

GLM 5.2 was Z.AI's open-weight flagship from June 16, 2026, with a 1M-token context, until GLM 5.3 replaced it in August. GLM 5.3 was post-trained on the GLM 5.2 base and scores far higher: Artificial Analysis gives GLM 5.2 34 on its Intelligence Index and 1.0% in its Terminal-Bench 4.0 run, against 45 and 41.9% for GLM 5.3. Both list at $1.40/$4.40 per million tokens, so they cost the same per request.

Sources: Artificial Analysis

GLM 5.2 FAQ

How much does GLM 5.2 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 5.2 charge more for long prompts?

No. GLM 5.2 bills the same rate per token up to its 1M-token context window.

How fast is GLM 5.2?

Artificial Analysis measures GLM-5.2 (Max) at 83 output tokens per second, with 27 seconds to the first answer token, thinking time included, on Z AI's API. Source: Artificial Analysis (artificialanalysis.ai).

Is GLM 5.2 good for AI agents?

Existing GLM 5.2 setups until they move to GLM 5.3. On our scoring, which is calibrated to public benchmarks, it rates 4.7/10 for agentic ability and 6.9/10 for output quality. Open weights.

What is GLM 5.2's context window?

GLM 5.2 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 5.2 open source?

Yes. GLM 5.2 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 5.2?

The main trade-offs: Superseded by GLM 5.3, which scores far higher at the same price; Weak on long agentic tasks (1.0% in Artificial Analysis's Terminal-Bench 4.0 run). It's strongest for existing GLM 5.2 setups until they move to GLM 5.3.