← Model list

GPT-5 Mini

openai·openai/gpt-5-mini·BETA·Closed·gpt-mini series

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

At a glance
Official price$0.25 / $2.00 per 1M
Cache read $0.025 · OpenAI
Lowest paid$0.04 / $0.29
QiHang Gateway · 7× spread
Context400,000
⚠ Providers report 200,000–400,000; the table below is authoritative
Output limit128,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2024-05-30
Released / updated2025-08-07 / 2025-08-07

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier medium

Intelligence31.6
Value308
Coding
Agentic
Output speed85 tok/s
TTFT12.91 s
Value formulaIQ 31.6 ÷ min blended $0.102 = 308
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
minimalIQ 14.3 · 94 tok/s
highIQ 25.8 · 83 tok/s
mediumIQ 31.6 · 85 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 31 providers29 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
QiHangGateway$0.04$0.29200,00064,000
PoeGateway$0.22$1.80$0.022400,000128,000
Jiekou.AIGateway$0.225$1.80400,000128,000
OrcaRouterGateway$0.25$2.00$0.025400,000128,000
NanoGPTGateway$0.25$2.00$0.025400,000128,000
ImpossiblGateway$0.25$2.00$0.025400,000128,000
OpenRouterGateway$0.25$2.00$0.025400,000128,000
Databricks
databricks-gpt-5-mini
Cloud$0.25$2.00$0.025400,000128,000
OpenAIOfficialFirst-party$0.25$2.00$0.025400,000128,000
VivgridGateway$0.25$2.00$0.03272,000128,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1QiHang$22.50
2Poe$110.24
3OrcaRouter$123.00
4NanoGPT$123.00
5Impossibl$123.00
6OpenRouter$123.00
8OpenAI · Official$123.00
Switch to QiHang to save $100.50/mo (82%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = higheffort = noneeffort = xhigheffort = max

4 / 31 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.00$02026-08-052026-08-132026-08-05 · Input list $0.252026-08-06 · Input list $0.252026-08-07 · Input list $0.252026-08-08 · Input list $0.252026-08-09 · Input list $0.252026-08-10 · Input list $0.252026-08-11 · Input list $0.252026-08-12 · Input list $0.252026-08-13 · Input list $0.252026-08-05 · Output list $2.002026-08-06 · Output list $2.002026-08-07 · Output list $2.002026-08-08 · Output list $2.002026-08-09 · Output list $2.002026-08-10 · Output list $2.002026-08-11 · Output list $2.002026-08-12 · Output list $2.002026-08-13 · Output list $2.002026-08-05 · Min blended $0.1022026-08-06 · Min blended $0.1022026-08-07 · Min blended $0.1022026-08-08 · Min blended $0.1022026-08-09 · Min blended $0.1022026-08-10 · Min blended $0.1022026-08-11 · Min blended $0.1022026-08-12 · Min blended $0.1022026-08-13 · Min blended $0.102