GLM 5.2 vs GLM 5.3
API pricing, context, and independently measured performance, side by side. GLM 5.2 starts 65% cheaper on input than GLM 5.3 at list prices.
GLM 5.2
Z.ai · released Jun 16, 2026
Best input$0.49 / MTok
Best output$1.54 / MTok
Context1.05M
Providers33
Fastest measured0.54s° TTFT · 131 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
GLM 5.3
Z.ai · released Aug 18, 2026
Best input$1.40 / MTok
Best output$4.40 / MTok
Context1.05M
Providers1
Fastest measured0.86s° TTFT · 52 tok/s
ToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| GLM 5.2 | BABaidu | $0.49 | $1.54 | 0.82s° | 72° tok/s | 3/5 |
| GLM 5.2 | SRSail Research | $0.50 | $3.15 | 1.5s° | 38° tok/s | 3/5 |
| GLM 5.2 | AMAmbient | $0.60 | $2.00 | 1.5s° | 167° tok/s | 3/5 |
| GLM 5.3 |  Z.AI | $1.40 | $4.40 | 0.86s° | 52° tok/s | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page