Deep Research Preview
deep-research-preview-04-2026Pricing
List prices at Google AI Studio, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.00 | $12.00 | |
| Batch 50% off | $1.00 | $6.00 | 50% off |
| Web search $35.00 per 1,000 searches | $35.00 per 1,000 searches |
What it costs a month
At Google AI Studio list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$1,500
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,392
- Coding agent1,000 requests a day, 40K in / 2K out$3,120
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$3,840
Where to run it
2 hosts serve Deep Research Preview. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
| $2.00 / $12.00 | deep-research-preview-04-2026 | ||
| $2.00 / $12.00 | deep-research-preview-04-2026 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesText
- Produces
- Text
- Features
- Built-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Google AI Studio.
Smaller Google models
- 11% less
- 11% less
- 25% less
Other frontier labs
- 11% less
- 11% less
- 33% less
- 56% less
Open-weight picks
- 3% less
- 11% less
- 52% less
- 56% less
Call it
Using Google AI Studio's API.
from google import genai
client = genai.Client() # reads GEMINI_API_KEY
response = client.models.generate_content(model="deep-research-preview-04-2026", contents="Hello")
print(response.text)curl "https://generativelanguage.googleapis.com/v1beta/models/deep-research-preview-04-2026:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Hello"}]}]}'from litellm import completion
response = completion(
model="gemini/deep-research-preview-04-2026",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Deep Research Preview cost?
On Google AI Studio, Deep Research Preview costs $2.00 per million input tokens and $12.00 per million output tokens.
Which APIs offer Deep Research Preview?
Deep Research Preview runs on 2 APIs: Google AI Studio and Vertex AI.
What is Deep Research Preview's context window?
1M tokens, with up to 66K tokens in one reply.
Is Deep Research Preview being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Deep Research Preview?
Models that cost less and keep most of what it can do: Gemini 4 Carbon on Google AI Studio (11% less), GPT-6.2 Sol on OpenAI (11% less), Claude Sonnet 5.5 on Anthropic (11% less) and Command A Plus on AIHubMix (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Deep Research Preview's API model id?
Use deep-research-preview-04-2026 with Google AI Studio.
Sources
Raw catalog entry for deep-research-preview-04-2026 on Google AI Studio
{
"input_cost_per_token": 0.000002,
"input_cost_per_token_batches": 0.000001,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0.000012,
"rpm": 1000,
"tpm": 4000000,
"output_cost_per_token_batches": 0.000006,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": false,
"supports_prompt_caching": false,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
}
}