Google · Image AI

Deep Research Preview (Apr-21-2026)

Catalog data · checked Nov 16, 2026

Deep Research Preview (Apr-21-2026) is a multimodal model from Google, released in April 2026. It reads text, images, video, audio and PDF files and writes text and images, with a context window of 1.05M tokens and up to 65.5K output tokens per answer. It costs $2 per million input tokens and $12 per million output tokens.

Calculate my costCompare

Input price$2per 1M tokens
Output price$12per 1M tokens
Context window1.05Mtokens per request
Max output65.5Ktokens per answer
ReleasedApr 20267 months ago
Knowledge cutoffJan 2025training data ends
WeightsClosedAPI only

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

More prices

Cached input (read)$0.2 /1M
Above 200K input tokens$4 in · $18 out

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$4.6
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out$0.324
10,000 product descriptions300 input and 200 output tokens per text$30
One day of agentic codingabout 3M input and 150K output tokens across many calls$7.8

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Questions & answers

How much does Deep Research Preview (Apr-21-2026) cost?

Deep Research Preview (Apr-21-2026) costs $2 per 1 million input tokens and $12 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Deep Research Preview (Apr-21-2026)?

Deep Research Preview (Apr-21-2026) can process up to 1,048,576 tokens per request and return up to 65,536 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does Deep Research Preview (Apr-21-2026) support tool calling?

Yes. The API accepts tool (function) definitions.