Scheduled for retirement on Sep 21, 2027. Still available at the prices below until then.
Context
400K
Max output
128K
Serving providers
6
Cheapest input
$0.75 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: ARC Prize and Artificial Analysis
Speed & latency
Output speed
233 t/s
tokens / second
Time to first token
133.61s
latency
Headline indices
56.1
of 100
Frozen Sep 9, 2026
19.7
of 100
Frozen Sep 9, 2026
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
Aa Analyst Agent0.1default—
AA-BriefcaseUndated10%default—
APEX Agents28%default—
ARC-AGI-219%xhigh$0.75
Automation Bench0.3default—
CritPt10%default—
GDPval v2Frozen Aug 18, 20261171.8default—
GPQA Diamond87%default—
Harvey Lab0.6default—
Humanity's Last Exam28%default—
IFBench73%default—
IT-Bench SRE35%default—
Long-Context Reasoning77%default—
Mlcr OverallFrozen Sep 9, 20260.0default—
MMMU-Pro73%default—
Omniscience-18.9default—
Omniscience Accuracy0.4default—
Omniscience Non Hallucination0.1medium—
SciCode52%default—
Terminal Bench400.0default—
TerminalBench Hard52%default—
TerminalBench v2.159%default—
τ-bench Banking26%default—
τ²-bench83%default—
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
We cannot tell whether this benchmark is still being published. Treat these scores as undated.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DatabricksCheapest$0.75$4.501
Standarddatabricks/databricks-gpt-5-4-mini
ComponentUnitStandard
Text cached in/1M tok$0.075
Text cache write/1M tok$0.75
Text input/1M tok$0.75
Text output/1M tok$4.50
Aihubmix$0.75$4.501
Azure$0.75$4.501
OpenAI$0.75$4.501
OpenRouter$0.75$4.501
VercelVercel reseller quote$0.75$4.501
OpenRouter (batch)$0.375$2.251
Vercel (flex)Vercel reseller quote$0.375$2.251
Vercel is dearest at $1.50 / $9.00

Price history

listed seller prices, input and output per 1M tokens
Input Output
$0.00$2.00$4.00$6.00Mar 17Jun 22Aug 26Sep 17$4.50$0.75

Cost calculator

estimate your monthly spend on this model
$510
estimated / month

Model IDs

copy the exact identifier for your platform
openai/gpt-5.4-mini:batchopenai/gpt-5.4-minidatabricks/databricks-gpt-5-4-minigpt-5.4-miniopenai/gpt-5.4-miniazure/gpt-5.4-miniopenai/gpt-5.4-miniaihubmix/gpt-5.4-miniopenai/gpt-5.4-mini-fastopenai/gpt-5.4-mini

Frequently asked questions

GPT-5.4 Mini pricing, context and availability

Is GPT-5.4 Mini still available?

Yes. GPT-5.4 Mini is scheduled for retirement on 2027-09-21.

How much does GPT-5.4 Mini cost?

GPT-5.4 Mini costs $0.75 per 1M input tokens from Databricks, and $4.50 per 1M output tokens from OpenAI. Across 6 serving providers, input prices range from $0.75 to $0.75 per 1M tokens.

What is the context window of GPT-5.4 Mini?

GPT-5.4 Mini accepts up to 400K tokens of context and can return up to 128K output tokens.

Which providers serve GPT-5.4 Mini?

GPT-5.4 Mini is available from 6 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.

What can GPT-5.4 Mini do?

GPT-5.4 Mini supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.

Other OpenAI models

compare pricing across the OpenAI lineup
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI