GLM 4.7 · Z.AI

What does GLM 4.7 cost to run in a coding agent?

GLM 4.7 costs about $0.017 per average coding-agent request on our measured traffic, at list prices of $0.60 per million input and $2.20 per million output tokens. It scores 22 on the Artificial Analysis Intelligence Index (an estimate), 38th 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

Run current Claude, GPT, Gemini and open models 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 4.7 costs per coding-agent request

Cost at list price	GLM 4.7
Prompt under 100K tokens50% of requests, 87% of input cached	$0.011
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.026
Prompt over 272K tokens11% of requests, 86% of input cached	n/a
Average request	$0.017
100 requests	$1.68
Median session16 requests; a session ends after 10 idle minutes	$0.19
A month of regular usemedian of 20 users active on 5+ days	$17.73

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. 20% of requests were larger than GLM 4.7's 205K context window and are left out of its figures.

GLM 4.7 benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	22 (estimate)	38 of 48
Output speedmedian	42 tokens/s	42 of 44
Time to first answer tokenincludes thinking time	49 s	22 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: GLM-4.7 (Reasoning). 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 4.7

GLM 4.7 is Z.AI's December 22, 2025 update to GLM 4.6, with modest gains at a similar price and the same 202K context. Artificial Analysis estimates 22 on its Intelligence Index, against 19 for GLM 4.6 and 45 for GLM 5.3, and lists it as superseded. Its 202K context is smaller than 19.7% of the coding-agent requests we measured.

Sources: Artificial Analysis

GLM 4.7 FAQ

How much does GLM 4.7 cost per coding-agent request?

$0.017 on average at list price, $1.68 per 100 requests, and $0.19 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 4.7 charge more for long prompts?

No. GLM 4.7 bills the same rate per token up to its 205K-token context window, which is smaller than 20% of the coding-agent requests we measured.

How fast is GLM 4.7?

Artificial Analysis measures GLM-4.7 (Reasoning) at 42 output tokens per second, with 49 seconds to the first answer token, thinking time included. Source: Artificial Analysis (artificialanalysis.ai).

Is GLM 4.7 good for AI agents?

Existing GLM 4.x setups that want a small step up from 4.6. On our scoring, which is calibrated to public benchmarks, it rates 4.7/10 for agentic ability and 5.3/10 for output quality. Open weights.

What is GLM 4.7's context window?

GLM 4.7 has a 205K-token context window. Z.AI is the maker.

Is GLM 4.7 open source?

Yes. GLM 4.7 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 4.7?

The main trade-offs: 202K context, smaller than 19.7% of the coding-agent requests we measured; Superseded by the GLM 5 line. It's strongest for existing GLM 4.x setups that want a small step up from 4.6.