AI model
z-ai/glm-5.3-flash:free
Z.ai: GLM 5.3 Flash (Free) is a 1,048,576-token model free on Composite. Ranked #1 of 179 models by traffic on Composite over the last 30 days, taking 41.19% of tokens and 40.1% of requests. 88% positive from 17 votes by Composite users who have run requests through the platform. Measured on Composite, 99.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 2704 ms, output runs at about 93.8 tokens per second.
Try in Playground| Model ID | z-ai/glm-5.3-flash:free |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text, image, video |
| Returns | text |
| Input price | Included in free allowance |
| Output price | Included in free allowance |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Always on for this model |
| Moderated | No |
| Cost on a monthly plan | Free - does not spend plan credits |
| Routing endpoints | 1 |
Make a Composite API key and type z-ai/glm-5.3-flash:free as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1.
Z.ai: GLM 5.3 Flash (Free) guide · JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#1 of 179
41.19% of tokens and 40.1% of requests over 30 days.
99.0%
Across the last 100 requests Composite served for this model.
2704 ms
Median across the same sample.
93.8 tok/s
Median generation rate after the first token.
44.5%
Share of prompt tokens served from the provider's cache over 7 days.
Free - 80 requests/day shared across free models; each call counts as 7
Credits pay the provider’s price plus 25%; cache hits cost less.
Monthly plans serve this model without spending any of their included credits.
cv11
GLM models balance strong instruction-following with competitive pricing, a reasonable middle ground for most roleplay setups.
With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is free on Composite, which makes it a reasonable place to test a character card, preset or lorebook before connecting your own provider.
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...
Supplied by cv11, not written by Composite.
Z.ai: GLM 5.3 FlashX Legal (Drafted) · Z.ai: GLM 5.3 Prime (Drafted) · Z.ai: GLM 5.3 FlashX (Drafted)