GLM 5.3 FlashX is a Z.ai model with 1M context, $0.37 in / $1.25 out per million tokens, last verified October 2, 2026. Open weights: not verified. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.
A separate Z.ai GLM 5.3 Flash-family endpoint with its own token pricing and a vendor throughput claim.
Recorded profile verification October 2, 2026·Individual provider fields may change
AI model specification details
Specification
GLM 5.3 FlashX
Provider
Z.ai
Tier
Budget
Context window
1M
Max output
Not verifiedUnverified
Input / 1M tokens
$0.37
Output / 1M tokens
$1.25
Weights
Not verifiedUnverified
Parameters
Not verifiedUnverified
Reasoning levels
Not verifiedUnverified
Modalities
text, image, video, file
API model id
glm-5.3-flashx
Released
Not verifiedUnverified
Pricing tiers: Z.ai $0.37/$1.25 per MTok; cached input $0.075, storage listed as limited-time free with no verified end date. The hosted guide advertises 1M context and 128K output. Exact release day is unverified.
Best for
Visual coding
High-throughput agents
Watch out
FlashX has its own endpoint and prices, and is not currently on Coding Plan. Thinking cannot be disabled. The shared guide says text parameters follow GLM-5.3, but a FlashX-specific effort table and exact numeric output ceiling are not separately verified. Z.ai advertises 200 tokens/s without a matched Flash comparison or full serving conditions. Weight availability and parameter counts remain unknown; do not inherit Flash specifications or benchmarks.
Source receipts
Catalog figures for this model were checked against the following sources.
Answered from the verified figures on this page rather than general guidance.
How much does GLM 5.3 FlashX cost per million tokens?
GLM 5.3 FlashX lists base rates of $0.37 per million input tokens and $1.25 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Z.ai $0.37/$1.25 per MTok; cached input $0.075, storage listed as limited-time free with no verified end date. The hosted guide advertises 1M context and 128K output. Exact release day is unverified.
What is GLM 5.3 FlashX's context window?
GLM 5.3 FlashX accepts about 1M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is GLM 5.3 FlashX best for?
GLM 5.3 FlashX is a budget tier from Z.ai. It suits visual coding, high-throughput agents. FlashX has its own endpoint and prices, and is not currently on Coding Plan. Thinking cannot be disabled. The shared guide says text parameters follow GLM-5.3, but a FlashX-specific effort table and exact numeric output ceiling are not separately verified. Z.ai advertises 200 tokens/s without a matched Flash comparison or full serving conditions. Weight availability and parameter counts remain unknown; do not inherit Flash specifications or benchmarks.
