Loading…
Z-AI
z-ai/glm-5.2Hugging Face ↗
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Only tracked on Vercel AI Gateway.
Vercel AI Gateway share of tokens, by day.
GLM 5.2 holds 3.46% today, up from 0.07% at the start of the visible window.
GLM 5.2's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-10-15, GLM 5.2 holds 0.0% of Vercel AI Gateway token share, down 0.95pp over 30 days. Data: Vercel AI Gateway as of 2026-10-15. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
GLM 5.2 is served by 32 tracked endpoints on OpenRouter. The cheapest output price is $0.59 per million tokens from Baidu · 1049k, and the most expensive is $10.00 from Wafer · 1049k. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Baidu · 1049k | $0.19 | $0.59 | 1049k | 100.00% |
| Inceptron | $0.69 | $1.04 | 1049k | 100.00% |
| DeepInfra · 1049k | $0.45 | $1.44 | 1049k | 100.00% |
| StreamLake | $0.56 | $1.75 | 1024k | 100.00% |
| DeepInfra · 1049k | $0.56 | $1.80 | 1049k | 100.00% |
| Novita | $0.65 | $2.04 | 1049k | 100.00% |
| DigitalOcean | $0.70 | $2.20 | 1049k | 100.00% |
| SiliconFlow | $0.70 | $2.20 | 1049k | 100.00% |
| CoreWeave | $0.62 | $2.42 | 1049k | 100.00% |
| AtlasCloud | $0.94 | $2.95 | 1049k | 100.00% |
| Phala | $1.26 | $3.00 | 1049k | 100.00% |
| Alibaba · 1000k | $0.97 | $3.04 | 1000k | 100.00% |
| Alibaba · 1000k | $1.12 | $3.52 | 1000k | 100.00% |
| Nebius | $1.40 | $4.40 | 1049k | 100.00% |
| Mistral · 1049k | $1.40 | $4.40 | 1049k | 100.00% |
| BaseTen · 1049k | $1.40 | $4.40 | 1049k | 100.00% |
| Together | $1.40 | $4.40 | 1049k | 100.00% |
| Venice | $1.40 | $4.40 | 1000k | 100.00% |
| GMICloud | $1.40 | $4.40 | 1049k | 100.00% |
| Parasail | $1.40 | $4.40 | 262k | 100.00% |
| Friendli | $1.40 | $4.40 | 1049k | 100.00% |
| Z.AI | $1.40 | $4.40 | 1049k | 100.00% |
| Mistral · 1049k | $1.54 | $4.84 | 1049k | 100.00% |
| Relace | $0.076 | $6.00 | 1049k | — |
| Morph | $0.080 | $6.00 | 1049k | 100.00% |
| BaseTen · 1049k | $2.10 | $6.60 | 1049k | 100.00% |
| Wafer · 1049k | $0.034 | $7.00 | 1049k | 100.00% |
| Alibaba · 1000k | $2.31 | $7.26 | 1000k | 100.00% |
| Baidu · 1049k | $2.25 | $7.88 | 1049k | 100.00% |
| Cloudflare | $0.19 | $8.00 | 262k | 100.00% |
| Decart | $2.50 | $9.00 | 1049k | 100.00% |
| Wafer · 1049k | $0.19 | $10.00 | 1049k | 100.00% |
Median dollars spent on one GLM 5.2 session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Claude Code | $0.013 | $0.061 | $0.339 | $2.62 |
| Kilo Code | — | $0.058 | $0.283 | — |
| Hermes Agent | $0.0004 | $0.027 | $0.248 | $1.60 |
