Sign in
Claude Code logo

Claude Code

Active

Anthropic's agentic coding tool for the terminal, IDE, desktop app and browser

Visit websiteCompare
Conditional

Claude Code is the most architecturally complete agentic coding tool we track: dynamic workflows, maker-checker sub-agents, cloud routines and a separate verifier model all ship in one engine across terminal, IDE, desktop and web. The condition is cost. Anthropic's own docs put the average at about $13 per developer per active day, or $150-250 per month, and agent teams use roughly 7x the tokens in plan mode. Right for teams that meter and cap spend.

AI-Native

The agent loop is the model: reads a step, acts, reads the result, and continues holding full context throughout the task.

Is it right for you?

Good for

  • Teams running autonomous coding loops with maker-checker verification, scheduled agentic tasks, and multi-agent orchestration across large codebases.

Not good for

  • Developers on a tight token budget — Anthropic's docs put the average enterprise cost at about $13 per developer per active day ($150-250 per developer per month), and agent teams use roughly 7x the tokens of a standard session in plan mode.

Our experience

We haven't tested Claude Code ourselves. This profile is based on public documentation, user reviews, and community feedback.

Pricing

Freemium
Pro$20/mo, or $17/mo billed annually
  • Includes Claude Code
  • Annual billing is $200 up front
  • Usage credits available to keep working past plan limits
MaxFrom $100/mo
  • Choose 5x or 20x more usage than Pro
Team (Standard seat)$25/seat/mo, or $20 billed annually
  • Includes Claude Code and Claude Cowork
  • Per-seat allowance shared with Claude chat and Cowork, resetting on 5-hour and weekly windows
Team (Premium seat)$125/seat/mo, or $100 billed annually
  • Includes Claude Code and Claude Cowork
Enterprise$20/seat + usage at API rates
  • Usage cost scales with model and task
View full pricing

Verdict history

Sep 30, 2026
conditional -> conditional (summary corrected: unsourced Uber anecdote replaced with Anthropic's own cost figures): The Uber budget anecdote had no fetched primary source. Anthropic's costs documentation gives the average per-developer figures and the agent-team token multiplier.

Sources

Verification log

  • Pricing· No changes

    Automated agent

  • Pricing· Needs attention

    Automated agent

  • Profile· Updated

    Automated agent

    Summary and strengths carried an unsourced Uber budget anecdote and em dashes. Replaced with Anthropic's documented figures: about $13 per developer per active day, $150-250 per month, agent teams roughly 7x tokens in plan mode. The June 15 separate credit pool claim and the weekly-limit change were not found on the fetched docs pages and are kept as stored, unverified.

  • Pricing· No changes

    Automated agent

    Pro, Max, Team Standard/Premium and Enterprise tiers match stored. Rating before: conditional, rating after: conditional.

  • Pricing· No changes

    Automated agent

    claude.com/pricing re-read 2026-09-23: Pro $20 monthly / $17 per month annual ($200 up front), Max from $100, Team Standard $20 annual / $25 monthly, Team Premium $100 annual / $125 monthly, Enterprise $20/seat/month billed annually plus usage at API rates; Claude Code included on all. Matches stored tiers. verdict_summary still carries the unsourced Uber anecdote (write path verdict_set, operator call); not touched. No update call, data_hash unchanged.

  • Pricing· No changes

    Automated agent

    claude.com/pricing re-read 2026-09-18: Pro $20 monthly / $17 annual ($200 up front), Max from $100, Team Standard $25/$20, Team Premium $125/$100, Enterprise $20/seat billed annually + usage; Claude Code included on all. All match stored tiers. No Sep 14 weekly-limit change on the page, so nothing written for that watch item. Not changed: verdict_summary still carries the unsourced Uber anecdote and em dashes (operator call, write path verdict_set). No update call, data_hash unchanged.

  • Profile· Updated

    Automated agent

    Tagline and description opening corrected against the official overview (fetched 2026-09-14): 'Available in your terminal, IDE, desktop app, and browser' and 'Claude Code runs on several surfaces: the terminal, IDE extensions, a desktop app, and the web.' Stored tagline 'Anthropic's terminal-based agentic coding tool' -> 'Anthropic's agentic coding tool for the terminal, IDE, desktop app and browser'; description sentence 'terminal-based agentic coding CLI' rewritten to name the four surfaces (VS Code and JetBrains extensions). Rest of description unchanged. Pricing re-read on claude.com/pricing: Pro $20 monthly / $17 annual ($200 up front), Max from $100, Team Standard $25/$20, Team Premium $125/$100, Enterprise $20/seat + API-rate usage; all match stored tiers. claude.com/pricing carries no Sep 14 weekly-limit change, so no refresh on that item (existing draft claude-code-weekly-limits-sep-14-cut-from-boost covers it). Not changed: verdict_summary still carries the unsourced Uber anecdote and em dashes (write path verdict_set; not vendor-evidenced, left for operator). No draft: a stale-surface correction, not a vendor event.

  • Profile· Updated

    Automated agent

    Law 1 correction: description said Claude Code 'Launched as a research preview in early 2026'. Anthropic's own announcement is dated February 24, 2025 and introduces Claude Code as 'available as a limited research preview' and 'our first agentic coding tool'. Stored date was wrong by a year; now 'Announced on February 24, 2025 as a limited research preview'. Also backfilled pricing_tiers, previously EMPTY, from claude.com/pricing (Max and Team lines re-read verbatim): Pro $20/mo or $17/mo annual ($200 up front), includes Claude Code; Max from $100/mo, 5x or 20x Pro usage; Team Standard $25/seat monthly or $20 annual; Team Premium $125 or $100; Enterprise $20/seat + usage at API rates. Team allowance text from code.claude.com/docs/en/costs. NOT changed, unconfirmed: the 'June 15, 2026 separate monthly credit pool ($20 Pro, up to $200 Max)' sentence. The costs doc describes plan allowances plus usage credits past the limit and names no separate automated pool, but absence is not contradiction, so stored text kept. Verdict unchanged. entity_id from backfill rows, and independently confirmed: a rejected INSERT this run echoed tool_id b55a46eb-1330-434e-8d53-2ed817244b59.

  • Pricing· No changes

    Automated agent

  • Pricing· No changes

    Automated agent

  • Pricing· No changes

    Automated agent

  • Pricing· No changes

    Automated agent

    June 15, 2026 billing split already captured in description. Current pricing model ($20 Pro/$100 Max 5x/$200 Max 20x credit pools) consistent with stored data from 2026-06-24 verify.

  • Profile· No changes

    Imported at launch

  • Pricing· No changes

    Imported at launch

How we evaluate

Want this running in your business?

We tested this tool and we build with tools like it every day. Tell us the workflow and we will set it up, integrate it and hand it over working.

Tell us what you need (opens in new tab)See what we build

The conversation runs on Gnosari, one of the tools in this directory. A real conversation, not a sales script.