Google DeepMind · Released 2026-10-06

Nano Banana 2.1

An image-generation and conversational-editing model; follow official examples, local edits, subject consistency and tool access.

Original model explanation ↗

No comparable leaderboard score is included yet. Explore the evaluations and examples below.

Evaluations: conditions and results

Official and provider materials explained

This update and region-specific editing →

Vercel describes two uses: placing an existing product in a different setting, and specifying an editing region with a mask or drawn strokes.

How this capability connects to works and uses

Google DeepMind model evolution

  1. Gemini 3.7 Flash → 3.8 Flash

    Flash advances coding, multi-step reasoning and agent work at the same speed and price positioning; Flash Cyber is a separate security-focused variant.

    Original release ↗
  2. Gemini 4 Argon

    The new generation is announced with access initially limited to invited testers; evaluation results do not establish public availability.

    Original release ↗
  3. Nano Banana 2.1

    Image generation and conversational editing advance, emphasizing local edits, subject consistency and text rendering.

    Original release ↗
  4. EmbeddingGemma 2

    The retrieval model extends text representations to images, audio and video, with public weights and phone demos.

    Original release ↗
  5. Gemini 4 Argon · 扩大开放

    The same model expands to the paid API, Gemini Pro/Ultra and development tools; shared context and long-decode conditions matter. Copilot has separate plans and gradual rollout.

    Original release ↗
  6. Genie 4

    A new generation of the real-time interactive world model: native audio, on-the-fly text steering and Gemini-planned multi-step events; a research preview reaches trusted testers first, then Project Genie for AI Ultra in coming weeks. No board entries — the scope gap stays stated.

    Original release ↗
  7. Gemini 4 Carbon

    A new frontier model: first on AA v5.0 at 59 (high), officially positioned for cybersecurity and long-horizon work. Access reaches a small group of cyber defenders this week, widens via Fairwind, and stays pending for developers and consumers; introductory pricing is $2/$10 per million tokens, later $4/$20. A high score is not general availability.

    Original release ↗
  8. Gemini 4 Carbon · 普遍开放

    Two weeks after launch, Carbon opens to all paying developers and enterprises via API (AI Studio / Gemini for business, still $2/$10 per million tokens introductory), and to AI Ultra subscribers in Antigravity, the Gemini app and AI Mode in Search; GitHub Copilot carries it the same day. The post adds new benchmark claims and behavior figures (agentic honesty 92% versus Argon’s 70%; adaptive-red-team per-attempt breach rate 0.8% versus 3.1%) and names AlphaProof Code’s Signal verification as a flagship use.

    Original release ↗
  9. Gemini Robotics 2.5

    The vision-language-action model rolls out to robotics partners: a kitting pilot on two active Mercedes lines reached 96% (proof-of-concept caliber), with success rates 30–100% above the previous baseline and tasks 20–30% faster across 200 tasks; Gemini 4 Argon accelerated training as a simulation engine. No public access; not applicable to the AA / Pi / Physics boards — details in our article.

    Original release ↗
  10. Gemini 4 Hydrogen

    The family adds an everyday-execution tier, available to everyone on day one: all AI Studio tiers, the Gemini API, business surfaces, the Gemini app and Google Search (paid Pro/Ultra also get Antigravity and Sheets); $1.5/$7.5 per million tokens flat across the 1M-token context, with four thinking levels including the new xhigh. The AA independent board lists xhigh 54 / high 51 (above Argon's high 50). Antigravity ships Orchestrator the same day, switching between Carbon and Hydrogen within a session — officially near-full-Carbon success on Terminal-Bench 4.0 with 24% less quota and 19% faster.

    Original release ↗
  11. Gemini 4 Neon

    The family's mid-tier arrives (a third new tier in 21 days): positioned for "frontier-level intelligence with fast end-to-end task completion across complex software engineering, knowledge work, and science workflows", with four thinking levels (Carbon has no xhigh) and a 1M-token context; $3/$15 per million tokens with cached input at $0.15 (a 95% discount). Access: the paid API, the Gemini app and Antigravity (Pro/Ultra), and business; generally available in GitHub Copilot from November 18 (Pro+/Max/Business/Enterprise, gradual rollout across ten surfaces, billed at provider list pricing); Tasks in the Gemini app can now run on Neon, and inside Antigravity Neon can act as an Orchestrator directing parallel Hydrogen subagents; Neon for cyber opens to trusted defenders via Fairwind in the coming days. The AA independent board lists four tiers — xhigh 61 / high 60 / medium 55 / low 44 (this site's direct full-board fetch, November 19) — and its highest setting, 61, ranks third overall, past Carbon's ceiling (high 60): the family's second inversion of the tier above.

    Original release ↗