Deep Research Preview API Pricing
As of October 10, 2026, Deep Research Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens on Google AI Studio. It has a 1,048,576-token context window and returns up to 65,536 tokens per response.
- Input
- $2.00 / 1M tokens
- Output
- $12.00 / 1M tokens
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Providers
- 1
- Added to LiteLLM
- September 24, 2026
Deep Research Preview pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Batch in | Batch out | Context |
|---|---|---|---|---|---|---|
| Google AI Studiosnapshot 04-2026 | gemini/deep-research-preview-04-2026 | $2.00 | $12.00 | $1.00 | $6.00 | 1M |
Other Deep Research Preview prices on Google AI Studio
| Web search | $35.00 per 1K searches |
What Deep Research Preview costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Google AI Studio | $10.00 |
| Google AI Studio batch | $5.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Google AI Studio | $22.40 |
Deep Research Preview features
Input: text, image. Output: text.
- Function calling
- Structured output
- Image input
- Prompt caching
- Web search
Use Deep Research Preview with LiteLLM
Call Deep Research Preview 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="gemini/deep-research-preview-04-2026",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: deep-research-preview
litellm_params:
model: gemini/deep-research-preview-04-2026
api_key: os.environ/GEMINI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "deep-research-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'Deep Research Preview FAQ
How much does Deep Research Preview cost?
Deep Research Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens on Google AI Studio. Batch requests cost $1.00 per 1M input tokens and $6.00 per 1M output tokens.
What is the context window of Deep Research Preview?
Deep Research Preview has a 1,048,576-token context window and returns up to 65,536 tokens per response.
Which providers offer Deep Research Preview?
Deep Research Preview is available from Google AI Studio through LiteLLM, using the model name gemini/deep-research-preview-04-2026.
How do I call Deep Research Preview with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gemini/deep-research-preview-04-2026", 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 Deep Research Preview support?
Deep Research Preview supports image input and web search. It does not support function calling, structured output and prompt caching.
When did LiteLLM add Deep Research Preview?
Deep Research Preview was added to LiteLLM's model price file on September 24, 2026.
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:
LiteLLM docs: Google AI Studio.
Provider pages: Google AI Studio.