---
schema_version: "newruntime-agent-readable-v0.2"
type: "capability_delta"
stable_id: "capability_delta:deep-research-previews-gain-registry-listed-million-token-context"
slug: "deep-research-previews-gain-registry-listed-million-token-context"
title: "Deep Research previews gain registry-listed million-token context windows"
description: "The models.dev registry raises both Deep Research preview context windows from 131,072 to 1,048,576 tokens, indicating room for larger research inputs. Runtime availability remains unconfirmed."
retrieval_nugget: "The models.dev registry raises both Deep Research preview context windows from 131,072 to 1,048,576 tokens, indicating room for larger research inputs. Runtime availability remains unconfirmed."
status: "published"
observed_at: "2026-11-09"
record_date: "2026-11-09"
date_kind: "observed_at"
before_capability: "Both Deep Research Preview and Deep Research Max Preview were listed with 131,072-token context windows."
enabling_change: "models.dev updated both Apr-21-2026 preview entries to list 1,048,576-token context windows."
after_capability: "The listed limits accommodate research inputs exceeding the previous 131,072-token ceiling, subject to runtime confirmation."
human_consequence: "Researchers could keep more source material in one context rather than splitting it into smaller inputs."
verification_level: "source-inspected"
buildability_class: "B0"
bottleneck: "The evidence establishes registry changes, not vendor-confirmed runtime support or effective use of the larger context."
related_shift: "shared-context-infrastructure"
related_posts: []
topics: []
source_urls: ["https://ai.google.dev/gemini-api/docs/models"]
featured: false
supporting_evidence: [{"title":"Google DeepMind Deep Research Preview (Apr-21-2026): context window 131,072 → 1,048,576 tokens","url":"https://ai.google.dev/gemini-api/docs/models","kind":"external","observed_at":"2026-11-09"},{"title":"Google DeepMind Deep Research Max Preview (Apr-21-2026): context window 131,072 → 1,048,576 tokens","url":"https://ai.google.dev/gemini-api/docs/models","kind":"external","observed_at":"2026-11-09"}]
routes: {"html":"https://newruntime.com/deltas/deep-research-previews-gain-registry-listed-million-token-context/","markdown":"https://newruntime.com/deltas/deep-research-previews-gain-registry-listed-million-token-context.md","json":"https://newruntime.com/deltas/deep-research-previews-gain-registry-listed-million-token-context.json"}
source_format: "knowledge-ledger"
published_at: "2026-11-17T05:08:11.198Z"
auto_created: true
editorial_provenance: {"desk":"knowledge-revision","provider":"codex","model":"gpt-6.1-sol","created_at":"2026-11-17T05:08:11.198Z","week_start":"2026-11-09","review":"auto-created from reviewed evidence; the owner may revise or retire it"}
---

# Deep Research previews gain registry-listed million-token context windows

## Retrieval answer

The models.dev registry raises both Deep Research preview context windows from 131,072 to 1,048,576 tokens, indicating room for larger research inputs. Runtime availability remains unconfirmed.

## Capability change

- Before: Both Deep Research Preview and Deep Research Max Preview were listed with 131,072-token context windows.
- Enabling change: models.dev updated both Apr-21-2026 preview entries to list 1,048,576-token context windows.
- After: The listed limits accommodate research inputs exceeding the previous 131,072-token ceiling, subject to runtime confirmation.

Human consequence: Researchers could keep more source material in one context rather than splitting it into smaller inputs.

Bottleneck: The evidence establishes registry changes, not vendor-confirmed runtime support or effective use of the larger context.

Buildability: B0. Verification: source-inspected. Related shift: [shared-context-infrastructure](https://newruntime.com/shifts/shared-context-infrastructure/).

Two matching registry updates indicate a context-capacity expansion across both Deep Research previews, rather than merely a price or model-name change.

If runtime support is confirmed, builders could assemble larger research source bundles in a single context, reducing input splitting.

Watch for vendor confirmation and runtime validation: the supplied evidence does not establish availability or research quality at the larger limit.

Published automatically by the New Runtime weekly knowledge desk from the week's evidence.

## Supporting evidence

- [Google DeepMind Deep Research Preview (Apr-21-2026): context window 131,072 → 1,048,576 tokens](https://ai.google.dev/gemini-api/docs/models) (external, 2026-11-09)
- [Google DeepMind Deep Research Max Preview (Apr-21-2026): context window 131,072 → 1,048,576 tokens](https://ai.google.dev/gemini-api/docs/models) (external, 2026-11-09)

## Provenance

Auto-created by the New Runtime weekly knowledge desk on 2026-11-17 from evidence reviewed in the week of 2026-11-09. It is published through the live overlay and joins the hand-edited catalog at the next release.
