ModelPickr

Compare / Google

Google · canonical pair

Gemma 4 26B A4B IT vs Gemma 4 31B IT

Alphabetical by model id, so this URL is the one to index. Gemma 4 26B A4B IT is google/gemma-4-26b-a4b-it. Gemma 4 31B IT is google/gemma-4-31b-it. Both are among the models the most providers list, inside the Google group.

A

Gemma 4 26B A4B IT

$1.80

per month at the reference workload

  • Reasoning
  • Tool use
  • Structured output
  • Vision
  • Long context
  • Open weights

vs

B

Gemma 4 31B IT

$1.44

per month at the reference workload

  • Reasoning
  • Tool use
  • Structured output
  • Vision
  • Long context
  • Open weights
100 requests a day, 2,000 input tokens and 500 output tokens, no cache hits. A light chat workload so the rate cards are comparable.
SpecGemma 4 26B A4B ITGemma 4 31B IT
Monthly, reference workload$1.80$1.44
Input / 1M$0.15$0.14
Output / 1M$0.60$0.40
Cache read / 1M$0.015—
Cache write / 1M——
Context262,144262,144
Max output32,76832,768
ReasoningYesYes
Tool callsYesYes
VisionYesYes
Open weightsYesYes
Providers2941
Released2026-04-022026-04-02

Same workload, your numbers

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Gemma 4 31B IT

$1.44

Cache hit is ignored because this model has no cache-read price.

Gemma 4 26B A4B IT costs $0.36 more per month than Gemma 4 31B IT at these inputs.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000