DeepSeek V3.2 vs GLM 5.1
API pricing, context, and independently measured performance, side by side. DeepSeek V3.2 starts 78% cheaper on input than GLM 5.1 at list prices.
DeepSeek V3.2
DeepSeek · released Dec 1, 2025
Best input$0.209 / MTok
Best output$0.31 / MTok
Context164K
Providers15
Fastest measured0.7s° TTFT · 102 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
GLM 5.1
Z.ai · released Apr 7, 2026
Best input$0.966 / MTok
Best output$3.04 / MTok
Context205K
Providers15
Fastest measured0.66s° TTFT · 190 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 | GMIGMICloud | $0.209 | $0.31 | 4.1s° | 33° tok/s | 5/5 |
| DeepSeek V3.2 | STStreamLake | $0.214 | $0.322 | 1.8s° | 28° tok/s | 5/5 |
| DeepSeek V3.2 | DIDigitalOcean | $0.25 | $0.80 | 0.7s° | 120° tok/s | 5/5 |
| GLM 5.1 | STStreamLake | $0.966 | $3.04 | 1.1s° | 48° tok/s | 2/5 |
| GLM 5.1 | CHChutes | $0.98 | $3.08 | 1.9s° | 79° tok/s | 3/5 |
| GLM 5.1 |  DeepInfra | $1.05 | $3.50 | 1s° | 13° tok/s | 2/5 |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · 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