GPT-5.4 nano pricing, context window and limits
GPT-5.4 nano costs $0.2 per million input tokens and $1.25 per million output tokens at OpenAI list price. It accepts up to 400,000 tokens of context and returns up to 128,000 tokens.
- Model id
gpt-5.4-nano - Snapshot
What does GPT-5.4 nano cost?
| Input | $0.2 |
|---|---|
| Output | $1.25 |
| Cached input (read) | $0.02 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can GPT-5.4 nano read and write?
| Context window | 400,000 |
|---|---|
| Max input | 272,000 |
| Max output | 128,000 |
What can GPT-5.4 nano do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image |
| Output | text |
What does a request to GPT-5.4 nano cost?
| A typical request: 1,000 tokens in, 500 out | $0.00082 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0032 |
| 1,000 typical requests | $0.82 |
| 1 million tokens in and 1 million out | $1.45 |
Input read from the provider's prompt cache costs $0.02 per million tokens instead of $0.2, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.00064 instead of $0.00082.
Among 49 OpenAI models with a published price, GPT-5.4 nano is the 8th cheapest by input price. Its context window is the 17th largest of 48. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GPT-5.4 nano through DVARA?
Configure the openai provider in the DVARA LLM Gateway and send the model id gpt-5.4-nano. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other OpenAI models are there?
- GPT-5.4 mini$0.75 in · $4.5 out · 400K context
- GPT-5.4 Pro$30 in · $180 out · 1.05M context
- GPT-5.4$2.5 in · $15 out · 1.05M context
- GPT-5.5$5 in · $30 out · 1.05M context
- GPT-5.3 Codex Spark$1.75 in · $14 out · 128K context
- GPT-5.5 Pro$30 in · $180 out · 1.05M context
- GPT-5.3 Codex$1.75 in · $14 out · 400K context
- GPT-5.6$4 in · $20 out · 1.05M context
- GPT-5.3 Chat (latest)$1.75 in · $14 out · 128K context
- GPT-5.6 Luna$0.2 in · $1.2 out · 1.05M context
- GPT-5.2 Pro$21 in · $168 out · 400K context
- GPT-5.6 Sol$4 in · $20 out · 1.05M context
Which models from other providers are similar to GPT-5.4 nano?
These are the closest in context window and input price, one per provider.
- Ministral 3 14BMistral AI · $0.2 in · $0.2 out · 262K context
- Qwen3-Coder 30B-A3B InstructAlibaba Qwen · $0.216 in · $0.861 out · 262K context
- Qwen3 235B-A22B Instruct 2507Amazon Bedrock · $0.22 in · $0.88 out · 262K context
- GLM-4.5-AirZhipu GLM · $0.2 in · $1.1 out · 131K context
- Gemini 3.1 Flash LiteGoogle Gemini · $0.25 in · $1.5 out · 1.05M context