Models / Z.ai
GLM 5.3 FlashX
by Z.ai ·
z-ai/glm-5.3-flashxGLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...
reasoningtool-usevisionreleased 2026-09-18
Legal score · raw
-
not yet benchmarked
Context
1.05M
max output 131K
Input
$0.46
per 1M tokens
Output
$1.56
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.11
4.1x cheaper than uncached
Uncached input
$0.46
per 1M tokens
Capabilities
Modalities
in textimagevideo
out text
Request parameters it accepts
include_reasoningmax_tokensreasoningreasoning_effortresponse_formattemperaturetool_choicetoolstop_ktop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.
Measured by DocketBuster
These numbers come from DocketBuster's own legal battery, not from DocketRouter's suite. Latest run per metric, with n and a 95% Wilson interval where the source reports one. See docketbuster.com/benchmarks.
| Metric | Value | n | Interval | Measured |
|---|---|---|---|---|
| Coaching quality (rubric, 0 to 8) | 7.32 / 8 | - | rubric mean, no interval reported | 2026-08-23 |