ModelPickr

Compare / GPT

GPT · canonical pair

GPT-5.4 mini vs GPT OSS 120B

Alphabetical by model id, so this URL is the one to index. GPT-5.4 mini is openai/gpt-5.4-mini. GPT OSS 120B is openai/gpt-oss-120b. Both are among the models the most providers list, inside the GPT group.

A

GPT-5.4 mini

$11.25

per month at the reference workload

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

vs

B

GPT OSS 120B

$1.80

per month at the reference workload

  • Reasoning
  • Tool use
  • Structured output
  • 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.
SpecGPT-5.4 miniGPT OSS 120B
Monthly, reference workload$11.25$1.80
Input / 1M$0.75$0.15
Output / 1M$4.50$0.60
Cache read / 1M$0.075$0.08
Cache write / 1M——
Context400,000131,072
Max output128,00032,768
ReasoningYesYes
Tool callsYesYes
VisionYesNo
Open weightsNoYes
Providers3244
Released2026-03-172025-08-05

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.

GPT-5.4 mini costs $9.45 more per month than GPT OSS 120B 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