GPT-5 Mini

openai · openai/gpt-5-mini

Small GPT-5 for responsive agents, coding help, and everyday automation

≈267k Chinese characters of context · Reads images · Step-by-step reasoning · Calls tools / agents · Structured JSON output

Read a 200,000-Chinese-character book and write a 2,000-Chinese-character summary: about $0.08

An order-of-magnitude estimate at 1.5 tokens per Chinese character and the vendor's own rate — not a quote. Full method: the glossary on the AI Models page.

Specs

Context400,000(≈267k Chinese characters)
Max output128,000
Structured outputYes
Open weightsNo
Released2025-08-07

Source: models.dev snapshot 2026-08-29

Who serves it, at what price

ProviderIn /MOut /MCache read /M
OpenAIfirst-party$0.25$2$0.025
302.AI$0.25$2
Abacus$0.25$2$0.025
Azure$0.25$2$0.03
Azure Cognitive Services$0.25$2$0.03
Cortecs$0.279$2.192$0.056
GitHub Copilot$0.25$2$0.025
Helicone$0.25$2$0.024999999999999998
Jiekou.AI$0.225$1.8
DevPass (LLM Gateway)$0.25$2$0.025
Neon$0.25$2$0.025
Pioneer$0.25$2$0.025
QiHang$0.04$0.29
SAP AI Core$0.25$2$0.025
Vivgrid$0.25$2$0.03

Rows tagged “first-party” are the model vendor's own pricing; untagged rows are resale channels and may differ.

When to choose it

We have not assessed this model. It comes from the full models.dev snapshot — the specs are the vendor's published figures, and a price is the vendor's own only on rows tagged first-party; the rest are resale channels. The fit is simply not something anyone here has written.

Leaderboard

Not yet on any leaderboard we track. That does not mean the model performs poorly — it means we have not taken this snapshot for it yet, and we do not publish a score we have not measured.