Z-AI
GLM 5.3 Flash
z-ai/glm-5.3-flashHugging Face ↗
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
Only tracked on Vercel AI Gateway.
GLM 5.3 Flash usage over time
Vercel AI Gateway share of tokens, by day.
GLM 5.3 Flash holds 8.12% today, up from 1.78% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
GLM 5.3 Flash'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 2026-10-09, GLM 5.3 Flash holds 8.1% of Vercel AI Gateway token share, up 1.03pp over 30 days. Source: Tidelines (Vercel AI Gateway).
Cost per session
Median dollars spent on one GLM 5.3 Flash 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 | $0.0025 | $0.0078 | $0.054 | $0.440 |
| Kilo Code | $0.0013 | $0.0087 | $0.043 | $0.356 |
| Hermes Agent | $0.0011 | $0.0054 | $0.037 | $0.258 |
| Codex | $0.0007 | $0.0047 | $0.025 | $0.052 |
Where to run it
GLM 5.3 Flash pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
GLM 5.3 Flash is served by 31 tracked endpoints on OpenRouter. The cheapest output price is $0.14 per million tokens from StreamLake, and the most expensive is $1.60 from Reka. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLake | $0.04 | $0.14 | 1024k | 100.00% |
| DeepInfra | $0.07 | $0.25 | 1049k | — |
| Novita | $0.08 | $0.28 | 1049k | 100.00% |
| GMICloud | $0.09 | $0.30 | 1049k | 100.00% |
| Decart | $0.09 | $0.31 | 1049k | 100.00% |
| Phala | $0.11 | $0.38 | 1049k | 100.00% |
| DigitalOcean | $0.13 | $0.44 | 1049k | 100.00% |
| Makora | $0.14 | $0.47 | 1049k | 100.00% |
| Relace | $0.04 | $0.50 | 1049k | 100.00% |
| Near AI | $0.08 | $0.50 | 1049k | 100.00% |
| Wafer | $0.10 | $0.50 | 1049k | 100.00% |
| Modal | $0.15 | $0.50 | 1049k | 100.00% |
| BaseTen | $0.15 | $0.50 | 1049k | 100.00% |
| Crusoe | $0.15 | $0.50 | 1049k | 100.00% |
| CoreWeave | $0.15 | $0.50 | 1049k | 100.00% |
| InferenceNet | $0.15 | $0.50 | 1049k | 100.00% |
| AtlasCloud | $0.15 | $0.50 | 1049k | 0.00% |
| Fireworks · 1049k | $0.15 | $0.50 | 1049k | 100.00% |
| Friendli | $0.15 | $0.50 | 1049k | 100.00% |
| SiliconFlow | $0.15 | $0.50 | 1049k | 96.67% |
| Together | $0.15 | $0.50 | 1049k | 100.00% |
| Parasail · 1049k | $0.15 | $0.50 | 1049k | 100.00% |
| Venice | $0.15 | $0.50 | 1049k | 100.00% |
| Z.AI | $0.15 | $0.50 | 1049k | 100.00% |
| Inceptron | $0.11 | $0.55 | 1049k | 100.00% |
| Sail Research | $0.04 | $0.60 | 1049k | 100.00% |
| Parasail · 1049k | $0.19 | $0.63 | 1049k | 100.00% |
| Fireworks · 1049k | $0.22 | $0.75 | 1049k | 100.00% |
| OpenInference | $0.04 | $0.90 | 1049k | 100.00% |
| Morph | $0.05 | $1.00 | 1049k | 56.67% |
| Reka | $0.06 | $1.60 | 262k | 100.00% |