Beta
Download

Gemini 4 Carbon vs Gemini 4 Argon: which to use for coding

AutoRouter10 min read

Key facts

As of November 10, 2026, keep everyday coding on Gemini 4 Argon, and bring in Gemini 4 Carbon for the hardest tasks: root-cause debugging across a large codebase, architecture changes, multi-package migrations and security audits. That is Google's own advice, published the day Carbon became generally available. The two models share one price list: $2 per million input tokens and $10 per million output tokens through November 30, 2026, then $4 and $20. Google says Carbon uses more tokens than Argon on each request, so any difference in cost comes from token counts. AutoRouter, the Mac app for Codex and Claude Code, wrote this post, has Gemini 4 Carbon in its model picker and worked the prices through: one assumed agent request costs $0.0345 on either model now and $0.069 from December 1.

Every outside figure below comes from the maker's or publisher's own page, linked where it is used and checked on November 10, 2026.

What is Gemini 4 Carbon?

Gemini 4 Carbon is the model Google calls its strongest, built for cybersecurity work and long agentic tasks in software engineering, knowledge work and science. Google announced it on October 28, 2026 and gave it first to cybersecurity defenders through its Fairwind Program. Gemini 4 Argon launched on October 13, 2026. As of November 10, 2026, Google's launch post and model page give these details, and Argon's page lists the same window, inputs and thinking levels:

Which coding work belongs on Carbon, and which stays on Argon?

Most coding stays on Gemini 4 Argon, and Gemini 4 Carbon takes the tasks that need the deepest reasoning. Google's November 10, 2026 post says Argon "remains the ideal choice for the majority of software engineering and knowledge work". Its developer docs split the work this way:

Kind of workGoogle points toWhy (Google, November 10, 2026)
Interactive coding and day-to-day feature workArgonThe docs say Argon answers faster and spends fewer tokens per request than Carbon.
Fast production loopsArgonThe docs say to keep Argon where speed matters.
Root-cause debugging in a complex codebaseCarbonCarbon spends more thinking tokens to explore and verify its work, which raises token use and latency.
Architectural design and multi-package migrationsCarbonThe launch post lists both as work Carbon does well, with several agents working together.
Security auditingCarbonThe docs list it, and Google's security benchmarks below cover this kind of work.
You aren't sure yetArgonGoogle describes it as the choice for most software engineering.

Google's docs also say to test at all three thinking levels and pick the lowest that meets your quality bar. Which model to use for which coding task maps the rest of your work to a model tier.

What does Gemini 4 Carbon cost next to Argon and other frontier models?

Gemini 4 Carbon costs the same per token as Gemini 4 Argon: $2 per million input tokens and $10 per million output tokens through November 30, 2026, and $4 and $20 from December 1 (Google's pricing page, as of November 10, 2026). From December 1, both match Claude Opus 5.5's input and output prices.

List price per million tokens, November 10, 2026Gemini 4 Carbon and Gemini 4 ArgonClaude Opus 5.5Claude Fable 5.2GPT-6 Astra
MakerGoogleAnthropicAnthropicOpenAI
Input$2 through November 30, then $4$4$8$10
Cached input$0.10 through November 30, then $0.20$0.20$0.20$1
Cache writeNone listed; caching is automatic$5 (5-minute), $8 (1-hour)$10 (5-minute), $16 (1-hour)$12.50 (30-minute), $25 (12-hour)
Output, thinking included$10 through November 30, then $20$20$40$50
Higher prices for long promptsNone listedNoneNoneOver 272,000 input tokens: $20 input, $75 output

The arithmetic below prices the assumed agent request this blog's pricing posts use: 45,000 cached input tokens, 5,000 new input tokens and 2,000 output tokens, thinking included. Google lists no cache-write price for either model, so new input bills at the input price. Caching is implicit, and the example assumes all 45,000 repeated tokens hit the cache, which Google's caching guide does not promise.

Assumed request: 45,000 cached input, 5,000 new input, 2,000 output tokens
Google's list prices per million tokens as of November 10, 2026
Gemini 4 Carbon and Gemini 4 Argon share these prices

Through November 30, 2026
  45,000 cached input  x  $0.10  =  $0.0045
   5,000 new input     x  $2.00  =  $0.0100  (no cache-write price listed)
   2,000 output        x $10.00  =  $0.0200
  Total                             $0.0345

From December 1, 2026
  45,000 cached input  x  $0.20  =  $0.0090
   5,000 new input     x  $4.00  =  $0.0200
   2,000 output        x $20.00  =  $0.0400
  Total                             $0.0690

Each extra 1,000 thinking or output tokens
  Through November 30: + $0.01     From December 1: + $0.02

At the launch price, $20 of API usage pays for 579 of these requests on Carbon or Argon, and for 289 from December 1. The same request costs $0.074 on Claude Opus 5.5 and $0.139 on Claude Fable 5.2, as worked in Claude Fable 5.2 vs Opus 5.5: which to use for coding. On GPT-6 Astra it costs $0.2075: $0.045 for cached input, $0.0625 for new input at the 30-minute cache-write price, and $0.10 for output. The arithmetic gives every model the same token counts, and real counts differ: Google says Carbon spends more thinking tokens on each request than Argon.

What does Google claim about Gemini 4 Carbon, and who measured it?

Google claims Gemini 4 Carbon leads three security benchmarks and Cursor's coding benchmark. As of November 10, 2026, Cursor's own page shows that coding lead at 0.4 points.

Security. In its October 28, 2026 post, Google reports 88.2% on SEC-bench Pro, which tests finding vulnerabilities in real software, 54.8% on ExploitGym, which tests exploiting them, and 71.0% on CWE-bench, which tests patching them. Google says these were evaluated without guardrails, and its November 10 post says Carbon leads them when accessed through the Fairwind Program. These scores describe security work. None of the three measures feature work or refactoring.

Coding. Google says Carbon ranks first on CursorBench 4.0, a set of long coding problems that Cursor runs, at less than half the cost per task of the next model from another maker. Cursor's page and Artificial Analysis's model pages list these results as of November 10, 2026, each model at its highest setting:

Result, as of November 10, 2026Gemini 4 Carbon (high)Gemini 4 Argon (high)Claude Opus 5.5 (max)Claude Fable 5.2 (max)GPT-6 Astra (max)
CursorBench 4.0 score, run by Cursor60.4%52.9%57.8%60.0%Not listed
CursorBench 4.0 cost per task$9.22$4.57$13.43$32.79Not listed
Artificial Analysis Intelligence Index v5.0.16050596557

Cursor notes that small differences in its scores may not be statistically meaningful. To judge your own work, run one hard task from your backlog on Carbon and on the model you use now.

How do you try Gemini 4 Carbon in Codex or Claude Code?

Use a gateway that lists the model, such as OpenRouter, or pick Gemini 4 Carbon in the model picker if you use AutoRouter. As of November 10, 2026, Google's docs have no guide for running Carbon inside either app.

AutoRouter has not run Carbon through OpenRouter for this post, so follow OpenRouter's guides for the exact settings. Try a new model in Codex or Claude Code without another API key covers both routes.

How does AutoRouter handle Gemini 4 Carbon?

Gemini 4 Carbon is in AutoRouter's model picker, where you can choose it yourself or name it in a plain-English rule. AutoRouter, the Mac app for Codex and Claude Code, puts new models in the picker you already use right away, with no keys or endpoints to set up.

Models outside your ChatGPT and Claude plans come with AutoRouter Pro, at $50 a month with $20 of included usage each month. Paid models bill at the provider's price plus 10%, which AutoRouter earns. The AutoRouter team tests every new model as it becomes available. AutoRouter runs on macOS 14 or later and is in beta, and requests pass through its servers on their way to each provider (AutoRouter privacy).

Questions

Is Gemini 4 Carbon better than Claude Fable 5.2 at coding?

It depends on the task. As of November 10, 2026, Carbon at high and Fable 5.2 at max are 0.4 points apart on Cursor's CursorBench 4.0, 60.4% to 60.0%, and Carbon's cost per task is $9.22 against $32.79. On the Artificial Analysis Intelligence Index, which also covers knowledge work and science, Fable 5.2 is listed at 65 and Carbon at 60. In Claude Code, Anthropic's models overview says to start most work on Claude Opus 5.5.

What does Gemini 4 Carbon cost after November 30, 2026?

From December 1, 2026, Gemini 4 Carbon costs $4 per million input tokens, $0.20 per million cached input tokens and $20 per million output tokens, twice the launch price (Google's pricing page, as of November 10, 2026). Gemini 4 Argon moves to the same prices on the same day. The assumed request above goes from $0.0345 to $0.069.

Should you raise Argon's thinking level or switch to Carbon?

Google's docs give no fixed order, so test both. They say to run your evaluations at low, medium and high and pick the lowest level that meets your quality bar (What's new in Gemini 4 Carbon). Moving from Argon to Carbon needs only the model ID changed to gemini-4-carbon.

Sources