# o3 Deep Research API Pricing

As of October 10, 2026, o3 Deep Research costs $10.00 per 1M input tokens and $40.00 per 1M output tokens on OpenAI, with cache reads at $2.50 per 1M tokens. It has a 200,000-token context window and returns up to 100,000 tokens per response.

- Page: https://models.litellm.ai/models/o3-deep-research
- Lab: OpenAI
- LiteLLM model name: `o3-deep-research`
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Added to LiteLLM: July 2025
- Deprecation date: July 23, 2026
- 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 | `o3-deep-research` | $10.00 | $40.00 | $2.50 | – | – | 200K |
| Azure OpenAI | `azure/o3-deep-research` | $10.00 | $40.00 | $2.50 | – | – | 200K |
| Azure OpenAI (eu) | `azure/eu/o3-deep-research` | $11.00 | $44.00 | $2.75 | – | – | – |
| Azure OpenAI (us) | `azure/us/o3-deep-research` | $11.00 | $44.00 | $2.75 | – | – | – |

## Cost examples

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

- OpenAI: $40.00
- Azure OpenAI: $40.00

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

- OpenAI: $108.00
- Azure OpenAI: $108.00

## Features

Supported: Image input, PDF input, Reasoning, Prompt caching, Web search.
Not supported: Function calling, Parallel tool calls, Structured output.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="o3-deep-research",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does o3 Deep Research cost?

o3 Deep Research costs $10.00 per 1M input tokens and $40.00 per 1M output tokens on OpenAI, with cache reads at $2.50 per 1M tokens.

### What is the context window of o3 Deep Research?

o3 Deep Research has a 200,000-token context window and returns up to 100,000 tokens per response.

### Which providers offer o3 Deep Research?

o3 Deep Research is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI.

### How do I call o3 Deep Research with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="o3-deep-research", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/responses from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does o3 Deep Research support?

o3 Deep Research supports image input, PDF input, reasoning, prompt caching and web search. It does not support function calling, parallel tool calls and structured output.

### When did LiteLLM add o3 Deep Research?

o3 Deep Research was added to LiteLLM's model price file in July 2025.

### Is o3 Deep Research being deprecated?

OpenAI deprecated o3-deep-research on July 23, 2026.

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