UseRightAI
HomeModelsAsk AIComparePricingWhat's New
UseRightAICut through AI hype. Pick what works.

Independent AI model tracker. Live pricing, real benchmarks, zero vendor bias.

X (Twitter)LinkedInUpdatesContact

Compare

Opus 4.8 vs Opus 4.7Fable 5 vs Opus 4.8New AI Models 2026ChatGPT vs ClaudeGPT-4o vs Claude SonnetClaude vs GeminiDeepSeek vs ChatGPTMistral vs ClaudeGemini Flash vs GPT-4o MiniLlama vs ChatGPTAll comparisons →Build your own →

Best For

CodingWritingDevelopersProduct ManagersDesignersSalesBest Cheap AIBest Free AI

Pricing & Data

API Token PricingCost per TaskPrice HistoryBenchmark ScoresPrivacy & SafetySubscription PlansPlan Usage LimitsCost CalculatorWhich AI is Cheapest?Cheapest AI APIs

Company

About UseRightAIContactWhat ChangedAll ModelsGuidesEditorial PolicyDisclosuresPrivacy PolicyTerms of Service

© 2026 UseRightAI. Independent · Free forever · Not affiliated with any AI provider.

Affiliate links are clearly labeled. See disclosures.

HomeAI Coding AgentsClaude Code

Coding Agent Guide

Claude Code: Pricing, Limits and Plans (October 2026)

AnthropicTerminal · IDE · Desktop app · Cloud agentVerified October 13, 2026

Quick answer

Claude Code is included in Claude Pro ($20/month, or $17/month billed annually) and every higher plan; the Free plan does not include it. Pro gives at least 5x Free's usage per rolling 5-hour session plus weekly limits, Max gives 5x or 20x Pro, and anything beyond can run on usage credits billed at API rates. Since late September 2026 it defaults to Claude Opus 5.5 on Pro.

Models: Claude models only — Claude Opus 5.5 by default on Pro and Max, Sonnet 5.5 and Haiku 5.5 selectable; Fable 5.1 on Max or via credits.

Plans and what they include

Official rows come from Anthropic's own pricing page; reported rows from press or trackers we could not confirm there.

PlanPriceWhat you get
Freeofficial$0Claude Code not included.Claude Code not included.
Proofficial$20/mo ($17/mo billed annually)Claude Code included. At least 5x Free's usage per 5-hour session, plus weekly limits; usage credits available past the cap.Claude Code included. At least 5x Free's usage per 5-hour session, plus weekly limits; usage credits available past the cap.
Max 5xofficial$100/mo5x Pro's usage per 5-hour session, weekly limits on top; Claude Fable 5.1 included up to 50% of weekly limits.5x Pro's usage per 5-hour session, weekly limits on top; Claude Fable 5.1 included up to 50% of weekly limits.
Max 20xofficial$200/mo20x Pro's usage per 5-hour session, weekly limits on top.20x Pro's usage per 5-hour session, weekly limits on top.
Team (standard seat)official$25/seat/mo ($20 billed annually)More usage than Pro; team includes up to $500/month in pooled API credits.More usage than Pro; team includes up to $500/month in pooled API credits.
Team (premium seat)official$125/seat/mo ($100 billed annually)5x a standard seat's usage.5x a standard seat's usage.
Enterpriseofficial$20/seat/mo billed annually + usage at API ratesUsage billed at API rates; cost scales with model and task.Usage billed at API rates; cost scales with model and task.
API keyofficialPay per tokenOpus 5.5 $4/$20, Sonnet 5.5 $2/$10, Haiku 5.5 $0.10/$0.50 per million tokens.Opus 5.5 $4/$20, Sonnet 5.5 $2/$10, Haiku 5.5 $0.10/$0.50 per million tokens.

How billing and limits work

  • Two meters run at once: a rolling 5-hour session allowance and a weekly limit. Hitting either pauses you until it resets.
  • Anthropic publishes multipliers (Pro is at least 5x Free; Max is 5x or 20x Pro), not message or token counts.
  • Claude Code and chat on claude.ai draw from the same allowance — a long coding session eats your chat budget too.
  • On paid plans you can switch on usage credits to keep working past the cap, billed at standard API rates.
  • Opus-class usage is tracked in its own weekly bucket, which is the one heavy users usually hit first.

Best for

  • Developers who already pay for Claude Pro — Claude Code costs nothing extra.
  • Long, multi-file changes in a terminal, where Claude Opus 5.5's coding strength matters most.
  • Heavy daily agent users on Max 20x, where a flat $200 beats metered API bills.

Watch out for

  • Claude models only — no switching to GPT or Gemini inside the tool.
  • Defaulting to Opus 5.5 drains the Opus weekly bucket fast; use /model to switch routine work to Sonnet 5.5.
  • Limits are compute-based and unpublished, so 'how much do I get' has no exact answer.

What changed, and when

September 28, 2026 official

Claude Sonnet 5.5 launches at $2/$10 on the API.

September 22, 2026 reported

Claude Opus 5.5 launches. Claude Code v2.1.280 switches the default on Pro and Team Standard from Sonnet to Opus 5.5. Anthropic announces higher 5-hour limits on paid plans without publishing amounts.

September 1, 2026 official

Claude Fable 5.1 launches: credits-only on Pro, included on Max up to 50% of weekly limits.

May 6, 2026 official

Anthropic doubles 5-hour session limits for Pro, Max, Team and seat-based Enterprise, and removes weekday peak-hour reductions.

FAQ

Is Claude Code free?

No. The Free Claude plan does not include Claude Code. The cheapest way in is Claude Pro at $20/month ($17/month billed annually), or an Anthropic API key billed per token.

Claude Code Pro or Max — which do I need?

Pro if you code with it for an hour or two a day. Max 5x ($100) once you hit Pro's weekly limit regularly, and Max 20x ($200) if Claude Code is your main tool all day. Anthropic sells the tiers as 5x and 20x Pro's per-session usage.

Which model does Claude Code use?

Claude Opus 5.5 by default on Pro and Max since late September 2026. You can switch to Sonnet 5.5 or Haiku 5.5 with /model; Sonnet 5.5 stretches your allowance much further for routine work.

What happens when I hit the Claude Code limit?

You wait for the 5-hour or weekly window to reset, or switch on usage credits, which bill at standard API rates. Settings → Usage shows both meters and their reset times.

Sources

  • Anthropic — Claude pricing (plans, Claude Code inclusion, usage credits)
  • Anthropic Help Center — usage limits

Coding-agent pricing changed for almost every vendor in 2026, often without notice. Everything above was checked against the linked sources on October 13, 2026; if you spot something outdated, email hello@userightai.com.

Compare with

All coding agents side by side →Claude Pro LimitsClaude Max LimitsClaude Opus 5 5Best Ai For Coding

Newsletter

Get an email when coding-agent pricing changes

Vendors change plans and limits quietly. We re-verify and log every change, dated.

No spam. Useful updates only. Affiliate disclosures always clearly labeled.