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
$0.20 /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 AnalysisSpeed & latency
Output speed
168 t/s
tokens / second
Time to first token
111.16s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| APEX Agents | 25% | default | — | |||||||||||||||||||||
| ARC-AGI-2 | 6% | xhigh | $0.16 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Automation Bench | 0.1 | default | — | |||||||||||||||||||||
| CritPt | 9% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1104.8 | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| GPQA Diamond | 82% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Harvey Lab | 0.5 | default | — | |||||||||||||||||||||
| Humanity's Last Exam | 28% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| IFBench | 76% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| IT-Bench SRE | 24% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Long-Context Reasoning | 77% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||||||||||
| MMMU-Pro | 65% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Omniscience | -18.0 | medium | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Omniscience Non Hallucination | 0.5 | medium | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| SciCode | 47% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Terminal Bench40 | 0.0 | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| TerminalBench Hard | 42% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| TerminalBench v2.1 | 61% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| τ-bench Banking | 27% | default | — | |||||||||||||||||||||
| τ²-bench | 76% | 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.
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 provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DatabricksCheapest | $0.20 | $1.25 | 1 | |||||||||||||||||
Standarddatabricks/databricks-gpt-5-4-nano
| ||||||||||||||||||||
| Aihubmix | $0.20 | $1.25 | 1 | |||||||||||||||||
Standardaihubmix/gpt-5.4-nano
| ||||||||||||||||||||
| Azure | $0.20 | $1.25 | 1 | |||||||||||||||||
Standardazure/gpt-5.4-nano
| ||||||||||||||||||||
| OpenAI | $0.20 | $1.25 | 1 | |||||||||||||||||
Standardgpt-5.4-nano
| ||||||||||||||||||||
| OpenRouter | $0.20 | $1.25 | 1 | |||||||||||||||||
Standardopenai/gpt-5.4-nano
| ||||||||||||||||||||
| VercelVercel reseller quote | $0.20 | $1.25 | 1 | |||||||||||||||||
Standardopenai/gpt-5.4-nano
| ||||||||||||||||||||
| OpenRouter (batch) | $0.10 | $0.625 | 1 | |||||||||||||||||
Batchopenai/gpt-5.4-nano:batch
| ||||||||||||||||||||
| Vercel (flex)Vercel reseller quote | $0.10 | $0.625 | 1 | |||||||||||||||||
Flexopenai/gpt-5.4-nano
| ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$140
estimated / month
Model IDs
copy the exact identifier for your platformopenai/gpt-5.4-nano:batchopenai/gpt-5.4-nanodatabricks/databricks-gpt-5-4-nanogpt-5.4-nanoopenai/gpt-5.4-nanoazure/gpt-5.4-nanoopenai/gpt-5.4-nanoaihubmix/gpt-5.4-nano
Frequently asked questions
GPT-5.4 Nano pricing, context and availabilityIs GPT-5.4 Nano still available?
Yes. GPT-5.4 Nano is scheduled for retirement on 2027-09-21.
How much does GPT-5.4 Nano cost?
GPT-5.4 Nano costs $0.20 per 1M input tokens from Databricks, and $1.25 per 1M output tokens from Databricks. Across 6 serving providers, input prices range from $0.20 to $0.20 per 1M tokens.
What is the context window of GPT-5.4 Nano?
GPT-5.4 Nano accepts up to 400K tokens of context and can return up to 128K output tokens.
Which providers serve GPT-5.4 Nano?
GPT-5.4 Nano is available from 6 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.
What can GPT-5.4 Nano do?
GPT-5.4 Nano 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