Gemma 4 26B A4B vs GLM 5.1
API pricing, context, and independently measured performance, side by side. Gemma 4 26B A4B starts 96% cheaper on input than GLM 5.1 at list prices.
Gemma 4 26B A4B
Google · released Apr 3, 2026
Best input$0.042 / MTok
Best output$0.20 / MTok
Context262K
Providers14
Fastest measured0.28s° TTFT · 87 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
GLM 5.1
Z.ai · released Apr 7, 2026
Best input$0.966 / MTok
Best output$3.04 / MTok
Context205K
Providers16
Fastest measured0.85s° TTFT · 22 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Gemma 4 26B A4B |  Darkbloom | $0.042 | $0.22 | 4.9s° | 58° tok/s | 5/5 |
| Gemma 4 26B A4B |  Reka | $0.06 | $0.20 | — | — | — |
| Gemma 4 26B A4B | DEDekaLLM | $0.06 | $0.33 | 1.7s° | 78° tok/s | — |
| GLM 5.1 |  StreamLake | $0.966 | $3.04 | 0.96s° | 63° tok/s | 2/5 |
| GLM 5.1 |  Chutes | $0.98 | $3.08 | 2.2s° | 98° tok/s | 3/5 |
| GLM 5.1 |  DeepInfra | $1.05 | $3.50 | 0.85s° | 22° 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