GPT-5.4 mini
Strong small GPT for coding subagents, quick tool use, and high-volume work
Cheapest input
$0.75
$/MTok · models.dev
Cheapest output
$4.50
$/MTok
Context
400K
tokens
Offers
1
1 source
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdatabricks-gpt-5-4-mini | Databricks | $0.75 | $4.50 | $0.075 | 400K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- Out: text
Knowledge cutoff: 2025-08-31Released: 2026-03-17Family: gpt-mini
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence40
- AA coding56.1
- AA agentic30.2
Sources: Arena AI, Artificial Analysis. See /benchmarks.