GLM 5.3 Flash
NEWZ.ai · Open weights · Released Aug 26, 2026 · z-ai/glm-5.3-flash
Best $0.075 in / $0.25 out via Z.AI · fp8 · 1.05M ctx at this price (headline 1.31M)
1.31M contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 10 providersUSD / MTOK · PRICES 6 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 Z.AI1ST PARTY | $0.075 | $0.25 | $0.015 | 1.05M | fp8 | — | — | 99.4% |
| GMIGMICloud | $0.075 | $0.25 | $0.015 | 1.05M | fp8 | — | — | 98.0% |
 Novita | $0.075 | $0.25 | $0.015 | 1.05M | fp8 | — | — | 99.5% |
 Venice | $0.094 | $0.313 | $0.019 | 1.05M | — | — | — | 54.2% |
| MOModal | $0.15 | $0.50 | $0.03 | 1.05M | fp8 | — | — | 90.7% |
 BaseTen | $0.15 | $0.50 | $0.03 | 1.05M | fp8 | — | — | 99.1% |
 Cloudflare | $0.15 | $0.50 | $0.03 | 1.31M | — | — | — | 98.5% |
 DeepInfra | $0.15 | $0.50 | $0.03 | 1.05M | fp8 | — | — | 99.4% |
| INIo Net | $0.15 | $0.50 | $0.03 | 262K | fp8 | — | — | 99.9% |
 Parasail | $0.15 | $0.50 | — | 1.05M | fp8 | — | — | 97.7% |
Pricing variants · USD / MTok in / out
STANDARD
$0.075 / $0.25
per MTok in / out
CACHE READ $0.015
Recent changesRSS ↗
Aug 27, 2026model added
About
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...
Specifications
Context window1,310,720
Max output131,072
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedAug 26, 2026
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/z-ai/glm-5.3-flash)Sources
OpenRouter API6 minutes ago
AGGREGATORHugging Face6 minutes ago
COMMUNITYVerified 6 minutes ago · list prices, not negotiated rates.