Loading…
Z-AI
z-ai/glm-5.3-20260816Hugging Face ↗
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
OpenRouter share of tokens, by day.
Z.ai: GLM 5.3 holds 2.82% today, up from 0.55% at the start of the visible window.
Z.ai: GLM 5.3'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 2026-10-14, Z.ai: GLM 5.3 holds 2.8% of OpenRouter token share, up 1.19pp over 30 days. Source: OpenRouter (openrouter.ai/rankings), as of 2026-10-14. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Z.ai: GLM 5.3 is served by 42 tracked endpoints on OpenRouter. The cheapest output price is $1.50 per million tokens from Sail Research, and the most expensive is $8.80 from Alibaba · 1000k. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Sail Research | $0.50 | $1.50 | 1049k | 100.00% |
| Inceptron | $0.55 | $1.50 | 1049k | 100.00% |
| Baidu | $0.60 | $1.88 | 1049k | 100.00% |
| SiliconFlow | $0.70 | $2.20 | 1049k | 100.00% |
| Novita | $0.70 | $2.20 | 1049k | 100.00% |
| Wafer · 1049k | $0.079 | $2.50 | 1049k | 100.00% |
| DeepInfra | $0.56 | $2.50 | 1049k | 100.00% |
| Tenstorrent | $0.60 | $2.50 | 1044k | 100.00% |
| Io Net | $0.49 | $2.60 | 262k | 100.00% |
| Phala | $0.84 | $2.64 | 1049k | — |
| Decart | $0.84 | $2.66 | 1049k | 100.00% |
| DigitalOcean | $0.91 | $2.86 | 1049k | 100.00% |
| DekaLLM | $0.18 | $2.95 | 1049k | 100.00% |
| GMICloud | $0.98 | $3.08 | 1049k | — |
| Alibaba · 1000k | $1.19 | $3.74 | 1000k | — |
| Friendli | $1.26 | $3.96 | 1049k | 100.00% |
| CoreWeave | $1.20 | $4.00 | 1049k | 81.82% |
| Reka | $0.14 | $4.20 | 262k | 100.00% |
| InferenceNet | $0.080 | $4.38 | 1049k | 100.00% |
| Relace | $0.063 | $4.40 | 1049k | 100.00% |
| Makora | $0.14 | $4.40 | 1049k | 96.67% |
| AkashML | $0.19 | $4.40 | 1049k | 100.00% |
| Mistral · 1049k | $1.40 | $4.40 | 1049k | 100.00% |
| BaseTen · 1049k | $1.40 | $4.40 | 1049k | 100.00% |
| Nebius | $1.40 | $4.40 | 1024k | — |
| Crusoe | $1.40 | $4.40 | 1049k | 100.00% |
| PrimeIntellect | $1.40 | $4.40 | 1049k | 100.00% |
| Venice | $1.40 | $4.40 | 1000k | — |
| Together | $1.40 | $4.40 | 1049k | 100.00% |
| Parasail | $1.40 | $4.40 | 1049k | 100.00% |
| Modal | $1.40 | $4.40 | 1049k | 100.00% |
| Fireworks · 1049k | $1.40 | $4.40 | 1049k | 100.00% |
| Cloudflare | $1.40 | $4.40 | 1049k | — |
| AtlasCloud | $1.40 | $4.40 | 1049k | 100.00% |
| Z.AI | $1.40 | $4.40 | 1049k | 100.00% |
| Wafer · 1049k | $0.18 | $4.80 | 1049k | 100.00% |
| Mistral · 1049k | $1.54 | $4.84 | 1049k | — |
| Morph | $0.080 | $6.00 | 1049k | 100.00% |
| ModelRun | $2.10 | $6.60 | 1049k | — |
| Fireworks · 1049k | $2.10 | $6.60 | 1049k | 100.00% |
| BaseTen · 1049k | $2.10 | $6.60 | 1049k | 100.00% |
| Alibaba · 1000k | $2.80 | $8.80 | 1000k | 100.00% |
Median dollars spent on one Z.ai: GLM 5.3 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 | $0.015 | $0.057 | $0.462 | $3.32 |
| Kilo Code | $0.025 | $0.084 | $0.451 | $2.62 |
| Hermes Agent | $0.0041 | $0.036 | $0.294 | $2.11 |
| Codex | $0.0054 | $0.028 | $0.232 | $0.794 |
