Gemini 4 Hydrogen, Argon, and Carbon: can you vibe-code on Google alone?

September ended with Argon still locked to Fairwind. Then Google opened Argon to everyone, shipped Carbon, then Hydrogen — in about a month. Here's the roster, the plan matrix, and whether Antigravity alone is a solid vibe-coding setup.

~9 min read

Gemini 4 Hydrogen, Argon, and Carbon — Google-only vibe coding

TL;DR

  • Google didn't slow down after September. Argon went live for everyone (not Fairwind-only), then Carbon, then Hydrogen — a full Gemini 4 ladder in about a month.
  • Google-only stack that actually works: Google AI Pro (~$20) + Antigravity. Use Hydrogen for everyday builds, Argon for hard planning, Carbon only on Ultra (or when Pro quotas die).
  • "Google-only" means Gemini models on purpose. Antigravity Pro also ships Claude Sonnet/Opus 5.5 — that's the escape hatch, not the thesis.
  • API: Hydrogen $1.50 / $7.50 (free tier in AI Studio). Argon and Carbon intro $2 / $10 through 30 Nov, then $4 / $20.

In my September 2026 AI recap, Gemini 4 Argon landed on 30 Sep as a frontier model you mostly couldn't use yet — Fairwind only, with a "keep 3.8 Flash warm" note.

That was the wrong read on Google's pace.

Flash had already been on a sprint (3.6 → 3.7 in three weeks). Then Argon went live for developers on 13 Oct, Carbon on 10 Nov, and Hydrogen on 12 Nov. The interesting question for vibe coding isn't "is Gemini competitive?" anymore. It's: if you only had Google — Antigravity, the Gemini app, and the Gemini API — would that be a solid setup?

This post is that answer: roster, prices, which plan unlocks which model, and a Google-only workflow. Rumors about Oxygen and Helix stay in their own section and stay labeled as rumors.

The Gemini 4 roster

Google's own positioning, translated into vibe-coding jobs:

Hydrogen

Build, test, iterate

Fast everyday coding and agentic execution. The daily driver once you're on Pro or Ultra in Antigravity — or free in AI Studio with rate limits.

$1.50 / $7.50 · free in AI Studio (rate-limited)

Argon

Plan + most hard work

Efficient frontier reasoning. Google says it's the right pick for the majority of software engineering and knowledge work.

$2 / $10 intro → $4 / $20 after 30 Nov

Carbon

When Argon is stuck

Strongest Gemini 4 model. Longer horizons, denser verification loops, more tokens per turn than Argon.

Same intro price as Argon · Ultra in Antigravity

Antigravity

Google's agent IDE

Desktop, CLI, and IDE where you pick Hydrogen, Argon, or Carbon (by plan). Free tier still runs 3.8 Flash — Gemini 4 coding needs Pro or Ultra.

Pro ~$20 · Ultra $100 / $200

Official announcements: Argon live for everyone · Carbon live · Hydrogen · Antigravity models.

Hydrogen "beats Argon" is Google's claim on the Artificial Analysis Intelligence Index at high thinking (51 vs 50; 54 at xhigh) — not a claim that Hydrogen replaces Argon for every hard architecture problem. Google still puts Carbon and Argon on deep judgment, and Hydrogen on rapid execution.

Prices and benchmarks

API list prices (as of mid-Nov 2026)

Swipe sideways for the full table →

ModelAPI idFree tierPaid in / out
per 1M tokens
Context
Gemini 4 Hydrogengemini-4-hydrogenYes (rate-limited)$1.50 / $7.50 flat1M unified
Gemini 4 Argongemini-4-argonNo$2 / $10 intro · $4 / $20 from 1 Dec1M unified
Gemini 4 Carbongemini-4-carbonNo$2 / $10 intro · $4 / $20 from 1 Dec1M unified

From Gemini API pricing. Intro prices for Argon and Carbon run through 30 Nov 2026. Cached input is discounted ~95% (Hydrogen ~$0.075; Argon/Carbon $0.10 intro, then $0.20). Thinking tokens count as output.

Scores worth caring about for coding

These are lab- or leaderboard-reported numbers, not my own bake-off. Labels matter.

Swipe sideways for the full table →

SignalHydrogenArgonCarbonWhere from
AA Intelligence Index51 high · 54 xhigh50~59 (v5.0 #1 at announce)Google / Artificial Analysis via Google posts
CursorBench 4.0 best · $/task——60.4% · $9.22 HighCursor leaderboard (cited in Fable 5.2 post)
FrontierCode 2.0——41.1% MediumAnthropic's Fable launch table
Terminal-Bench 4.157% vs 18.2% on 3.8 Flash——Google Hydrogen post

Google-reported figures from the Hydrogen and Carbon announcement posts; CursorBench from Cursor's public board as of the Fable 5.2 comparison sheet (13 Nov). FrontierCode row for Carbon is Anthropic-reported, not Google's. "—" = no number in the sources above.

Takeaway. Carbon is the CursorBench bargain at intro prices (Sonnet-level $/M, Fable-adjacent score). Argon is Google's "most of the work" frontier model. Hydrogen is the cheap, fast execution layer — and on some aggregate indexes Google says it edges Argon while finishing faster.

Which plan gets which model

This is the part that decides whether "Google only" is real or marketing.

Antigravity (the agent IDE)

From Google's Antigravity models docs:

Swipe sideways for the full table →

ModelFree & AI PlusAI Pro (~$20)AI Ultra ($100 / $200)
Gemini 3.8 FlashYesYesYes
Gemini 4 HydrogenNoYes (paid non-trial)Yes
Gemini 4 ArgonNoYes (paid / eligible device trial)Yes
Gemini 4 CarbonNoNoYes
Claude Sonnet / Opus 5.5NoYes (paid non-trial)Yes

Free and AI Plus share a column in Antigravity: you get 3.8 Flash (and older partner models that Google says drop on 18 Nov), not Hydrogen. Argon needs a paid Pro plan or an eligible premium-device trial; Hydrogen and Claude 5.5 need paid non-trial Pro.

Per Google AI subscriptions:

API / AI Studio

Setup for Antigravity itself is already covered in Free Google AI tools for vibe coding. The $20 fit guide for Pro vs Cursor vs Claude is in Which AI coding tool should you pay $20 for?.

The Claude escape hatch. Antigravity on Pro is not a Gemini-only product. It also lists Claude Sonnet 5.5 and Opus 5.5. If your experiment is "Google only," you have to ignore those rows on purpose. If your experiment is "one $20 agent IDE," Claude inside Antigravity is a feature, not a failure.

A Google-only vibe-coding workflow

Assume the constraint: no Cursor, no Claude Code, no ChatGPT Codex as the daily path. Only Google surfaces.

$0 — try Gemini, don't pretend it's a full agent stack

~$20 Google AI Pro — the real Google-only setup

  1. Hydrogen in Antigravity for everyday features, bug fixes, tests, and deploys — the daily build model.
  2. Argon for architecture, auth, payments, nasty concurrency, or multi-repo migrations — plan and hard judgment.
  3. AI Studio / API with the same model ids when you want a prompt playground or a script outside the agent IDE.
  4. Stay off Claude in the Antigravity picker if you're testing the Google-only thesis. Switch to Claude only when you decide the experiment failed for that task.

~$100+ Ultra — when Pro isn't enough

Honest framing. This is editorial, not a week of production-only Antigravity logs. The stack is coherent on paper: Hydrogen builds, Argon plans, Carbon escalates — all inside Antigravity (or AI Studio/API). Whether you personally drop Cursor depends on habits, quotas, and how often you reach for Claude in the same picker.

Cross-vendor ladder (VCL framing)

Google doesn't publish this table. I do — as a roles map, not a capability claim that Helix equals Luna.

Swipe sideways for the full table →

RoleGoogle (Gemini 4)OpenAIAnthropic
Cheap / fast / liteHelix rumorLunaHaiku
Daily buildHydrogenTerraSonnet
Plan + hard judgmentArgonSolOpus
When stuckCarbonAstraFable

Editorial mapping for vibe-coding jobs: Hydrogen ↔ Terra ↔ Sonnet; Argon ↔ Sol ↔ Opus; Carbon ↔ Astra ↔ Fable. Luna/Haiku sit with rumored Helix. Helix is unverified. For Anthropic pricing and when Fable earns its tokens, see Claude Fable 5.2 for vibe coding.

Rumors: Oxygen and Helix

Neither name appears on Google's official Gemini 4 list (Carbon, Argon, Hydrogen). Treat everything below as unverified.

If either ships, the Google-only ladder gets a true lite tier under Hydrogen. Until then, free Antigravity stays on 3.8 Flash, and AI Studio's free Hydrogen is the cheap Gemini 4 on-ramp.

Want next week's model notes before everyone else?

Subscribe to Vibe Coder's Life →

FAQ

Can you vibe-code on Google alone with Gemini 4?

Yes, if "alone" means Google AI Pro + Antigravity on Gemini models (Hydrogen for everyday builds, Argon for hard planning). Free tier alone is not a full Gemini 4 agent stack in Antigravity — you stay on 3.8 Flash there. Ultra unlocks Carbon.

Is Gemini 4 Hydrogen free?

On the Gemini API and in Google AI Studio, yes, with rate limits. In Antigravity, Hydrogen needs Google AI Pro (paid non-trial) or Ultra. The Gemini app can route free users to Hydrogen via auto selection.

Do I need Google AI Ultra for vibe coding?

Only if you need Carbon, or Pro quotas aren't enough. Most of Google's "majority of software engineering" pitch sits on Argon, which Pro already unlocks.

When do Argon and Carbon leave intro pricing?

After 30 Nov 2026. List price moves from $2 / $10 to $4 / $20 per million input/output tokens (API).

What about Oxygen and Helix?

Rumors only as of mid-Nov 2026. No official Google announcement, no public API ids to treat as shipping products.

Sources: Google DeepMind Gemini 4 Argon / Carbon / Hydrogen posts; Antigravity models; Gemini API pricing; Google AI subscriptions. Checked mid-Nov 2026. Full checklist in the repo sources file.

Disclosure: No sponsorship in this post. Benchmarks are Google-, Anthropic-, or Cursor-reported as labeled. Prices are USD list prices. Oxygen and Helix are unverified rumors.

Questions? Get in touch — or subscribe for the next issue.

← All posts