GPT-5.4 Nano API Pricing
As of October 10, 2026, GPT-5.4 Nano costs $0.20 per 1M input tokens and $1.25 per 1M output tokens on OpenAI, with cache reads at $0.02 per 1M tokens. It has a 272,000-token context window and returns up to 128,000 tokens per response.
gpt-5.4-nano.- Input
- $0.20 / 1M tokens
- Output
- $1.25 / 1M tokens
- Cache read
- $0.02 / 1M tokens
- Context window
- 272,000 tokens
- Max output
- 128,000 tokens
- Providers
- 6
- Added to LiteLLM
- March 2026
GPT-5.4 Nano pricing by provider
11 listings across 6 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Batch in | Batch out | Context |
|---|---|---|---|---|---|---|---|---|
| OpenAI | gpt-5.4-nano | $0.20 | $1.25 | $0.02 | – | $0.10 | $0.625 | 272K |
| OpenAIsnapshot 2026-03-17 | gpt-5.4-nano-2026-03-17 | $0.20 | $1.25 | $0.02 | – | $0.10 | $0.625 | 272K |
| AIHubMix | aihubmix/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | – | – | – | 400K |
| Azure AI Foundry | azure_ai/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | – | – | – | 272K |
| Azure AI Foundrysnapshot 2026-03-17 | azure_ai/gpt-5.4-nano-2026-03-17 | $0.20 | $1.25 | $0.02 | – | – | – | 272K |
| Azure OpenAI | azure/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | – | $0.10 | $0.625 | 272K |
| Azure OpenAIsnapshot 2026-03-17 | azure/gpt-5.4-nano-2026-03-17 | $0.20 | $1.25 | $0.02 | – | $0.10 | $0.625 | 272K |
| Databricks | databricks/databricks-gpt-5-4-nano | $0.20 | $1.25 | $0.02002 | $0.20 | – | – | 272K |
| Perplexity | perplexity/openai/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | – | – | – | – |
| Azure OpenAIeu | azure/eu/gpt-5.4-nano | $0.22 | $1.375 | $0.022 | – | $0.11 | $0.6875 | – |
| Azure OpenAIus | azure/us/gpt-5.4-nano | $0.22 | $1.375 | $0.022 | – | $0.11 | $0.6875 | – |
Other GPT-5.4 Nano prices on OpenAI
| Flex input | $0.10 per 1M tokens |
| Flex output | $0.625 per 1M tokens |
| Web search | $10.00 per 1K searches |
What GPT-5.4 Nano costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $1.025 |
| Databricks | $1.025 |
| AIHubMix | $1.025 |
| Azure AI Foundry | $1.025 |
| OpenAI batch | $0.5125 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $2.25 |
| Databricks | $2.25 |
| AIHubMix | $2.25 |
| Azure AI Foundry | $2.25 |
GPT-5.4 Nano features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Web search
Use GPT-5.4 Nano with LiteLLM
Call GPT-5.4 Nano through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-5.4-nano",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-5.4-nano
litellm_params:
model: gpt-5.4-nano
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-5.4-nano",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-5.4 Nano FAQ
How much does GPT-5.4 Nano cost?
GPT-5.4 Nano costs $0.20 per 1M input tokens and $1.25 per 1M output tokens on OpenAI, with cache reads at $0.02 per 1M tokens. Batch requests cost $0.10 per 1M input tokens and $0.625 per 1M output tokens.
What is the context window of GPT-5.4 Nano?
GPT-5.4 Nano has a 272,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-5.4 Nano?
GPT-5.4 Nano is available from 6 providers through LiteLLM: OpenAI, AIHubMix, Azure AI Foundry, Azure OpenAI, Databricks and Perplexity. The lowest price is on Databricks.
How do I call GPT-5.4 Nano with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-5.4-nano", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-5.4 Nano support?
GPT-5.4 Nano supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.
When did LiteLLM add GPT-5.4 Nano?
GPT-5.4 Nano was added to LiteLLM's model price file in March 2026.
Is GPT-5.4 Nano being deprecated?
OpenAI lists a deprecation date of April 1, 2027 for gpt-5.4-nano.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- aihubmix.com/api/v1/models
- ai.azure.com/catalog/models/gpt-5.4-nano
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
LiteLLM docs: OpenAI, AIHubMix, Azure AI Foundry, Azure OpenAI, Databricks, Perplexity.
Provider pages: OpenAI, AIHubMix, Azure AI Foundry, Azure OpenAI, Databricks, Perplexity.
