GLM 5.3 FlashX
Z.ai · Proprietary · Released Sep 18, 2026 · z-ai/glm-5.3-flashx
Best $0.37 in / $1.25 out via Z.AI · fp8
1.05M contextVisionToolsReasoningStructured outputPrompt caching
Available from 2 providersUSD / MTOK · PRICES 21 MINUTES AGO · SPEED 2 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 CheaperInferenceDIRECTMARKETPLACE | $0.24 | $0.81 | — | — | — | ✕ | ✕ | — |
 Z.AI1ST PARTY | $0.37 | $1.25 | $0.075 | 1.05M | fp8 | 1s | 149 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 2 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.37 / $1.25
per MTok in / out
CACHE READ $0.075
Recent changesRSS ↗
Oct 23, 2026endpoint added · cheaperinference1 → 2
Sep 19, 2026model added
About
GLM-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...
Specifications
Context window1,048,576
Max output131,072
Modalities intext, image, video
Modalities outtext
LicenseProprietary
ReleasedSep 18, 2026
TokenizerOther
Related
Embed badge
[](https://modelindex.ai/models/z-ai/glm-5.3-flashx)Sources
OpenRouter API21 minutes ago
AGGREGATORModelIndex benchmarks4 days ago
MEASUREDVerified 21 minutes ago · list prices, not negotiated rates.