# GPT-5 Nano API Pricing

As of October 10, 2026, GPT-5 Nano costs $0.05 per 1M input tokens and $0.40 per 1M output tokens on OpenAI, with cache reads at $0.005 per 1M tokens. Across 7 providers on LiteLLM, the input price ranges from $0.04998 to $0.15. It has a 272,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/gpt-5-nano
- Lab: OpenAI
- LiteLLM model name: `gpt-5-nano`
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Added to LiteLLM: August 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| OpenAI | `gpt-5-nano` | $0.05 | $0.40 | $0.005 | – | – | 272K |
| OpenAI (snapshot 2025-08-07) | `gpt-5-nano-2025-08-07` | $0.05 | $0.40 | $0.005 | – | – | 272K |
| Azure OpenAI | `azure/gpt-5-nano` | $0.05 | $0.40 | $0.005 | – | – | 272K |
| Azure OpenAI (snapshot 2025-08-07) | `azure/gpt-5-nano-2025-08-07` | $0.05 | $0.40 | $0.005 | – | – | 272K |
| Databricks | `databricks/databricks-gpt-5-nano` | $0.04998 | $0.40 | $0.00497 | – | – | 272K |
| Oracle Cloud (OCI) | `oci/openai.gpt-5-nano` | $0.05 | $0.40 | – | – | – | 272K |
| Perplexity | `perplexity/openai/gpt-5-nano` | $0.05 | $0.40 | $0.005 | – | – | – |
| Replicate | `replicate/openai/gpt-5-nano` | $0.05 | $0.40 | – | – | – | – |
| Snowflake Cortex | `snowflake/openai-gpt-5-nano` | $0.15 | $0.60 | – | – | – | 5M |
| Azure OpenAI (eu) | `azure/eu/gpt-5-nano` | $0.055 | $0.44 | $0.0055 | – | – | – |
| Azure OpenAI (eu, snapshot 2025-08-07) | `azure/eu/gpt-5-nano-2025-08-07` | $0.055 | $0.44 | $0.0055 | – | – | 272K |
| Azure OpenAI (us) | `azure/us/gpt-5-nano` | $0.055 | $0.44 | $0.0055 | – | – | – |
| Azure OpenAI (us, snapshot 2025-08-07) | `azure/us/gpt-5-nano-2025-08-07` | $0.055 | $0.44 | $0.0055 | – | – | 272K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- OpenAI: $0.30
- Databricks: $0.30
- Azure OpenAI: $0.30
- Oracle Cloud (OCI): $0.30
- OpenAI batch: $0.15

100 long-document requests with 100,000 input and 2,000 output tokens each:

- OpenAI: $0.58
- Databricks: $0.5798
- Azure OpenAI: $0.58
- Oracle Cloud (OCI): $0.58

## Features

Supported: Function calling, Parallel tool calls, Structured output, Image input, PDF input, Reasoning, Prompt caching, Web search.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gpt-5-nano",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-5 Nano cost?

GPT-5 Nano costs $0.05 per 1M input tokens and $0.40 per 1M output tokens on OpenAI, with cache reads at $0.005 per 1M tokens. Batch requests cost $0.025 per 1M input tokens and $0.20 per 1M output tokens. Across 7 providers on LiteLLM, the input price ranges from $0.04998 to $0.15.

### What is the context window of GPT-5 Nano?

GPT-5 Nano has a 272,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer GPT-5 Nano?

GPT-5 Nano is available from 7 providers through LiteLLM: OpenAI, Azure OpenAI, Databricks, Oracle Cloud (OCI), Perplexity, Replicate and Snowflake Cortex. The lowest price is on Databricks.

### How do I call GPT-5 Nano with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-5-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 Nano support?

GPT-5 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 Nano?

GPT-5 Nano was added to LiteLLM's model price file in August 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json