Tag: developer tools

  • Claude Code: Setup, Pricing, Limits & Picking Your Dev Tool

    Claude Code: Setup, Pricing, Limits & Picking Your Dev Tool

    Last verified: November 2026. Claude Code is Anthropic's terminal coding tool — it lives where developers live, in the command line. Around it has grown a small universe: install paths, seat pricing, credit pools, rate limits, and three sibling agent surfaces that people constantly confuse with it. This guide is the map.

    Installing it: two minutes, pick your path

    On Windows, it's PowerShell, one command, no Node.js required — the native install path, verified against the May 2026 installer, including the five errors you’ll hit and the exact fix for each. For the general path, it's the one-line npm CLI install plus the Desktop app, done in under two minutes, with the common errors covered.

    → Install Claude Code on Windows: 2026 Step-by-Step — the Windows path: one command, five errors, five fixes.

    → Install Claude Code: Complete Desktop & CLI Setup Guide — the general path: npm one-liner, Desktop app, troubleshooting.

    What it costs: seats, tiers, and the API meter

    Claude Code rides on your existing seat — Pro ($20/month), Max ($100/month), Ultra ($200/month), Team, or Enterprise. The API path is a separate console meter, not drawn from your seat. If you're deciding between Pro and Max for dev work, the question is usage volume: Max is for the people who live in the terminal all day.

    → Claude Code Pricing in 2026: Pro vs Max vs API Costs Explained — seats vs API, verified September 2026, with current token rates on the pricing hub.

    → Claude Code Pricing 2026: Pro, Max, and API Limits — the tier comparison for dev workflows, including Opus 5.5 API rates.

    How the billing actually works: subscriptions vs credit pools

    This is the part that surprises people. Interactive terminal use draws on your Pro/Max subscription — it's part of the seat. But since June 15, 2026, Agent SDK and headless (claude -p) usage moved to separate monthly billing. Same tool, two meters, depending on how you invoke it. Know which one you're on before the invoice teaches you.

    → Claude Code Billing & Monthly Credit Pools (2026) — subscription draw vs separate Agent billing, and how the credit pools work.

    The limits: two clocks

    Claude Code meters two clocks: a rolling 5-hour session window and a weekly bucket. The +50% weekly promo ended September 13, 2026 — what replaced it is a permanent +25% on the weekly limits. Note the model gating: Fable 5.1 is included only on Max and premium seats.

    → Claude Code Limits (September 2026) — both clocks explained, what's permanent, and where Fable 5.1 is available.

    Picking your surface: Cowork vs Code vs Agent SDK vs Managed Agents

    Anthropic now has four agent surfaces and they are not interchangeable: Claude Code, Claude Cowork, the Agent SDK, and Managed Agents. Interactive vs autonomous is the real dividing line — which surface fits depends on who's driving and how much autonomy the job needs.

    → Claude Cowork vs Code vs Agent SDK vs Managed Agents (2026) — the decision matrix: who each surface is for and where each runs.

    Cowork in action: the daily briefing

    The canonical Cowork workflow: connect your calendar, email, and tasks, write the right prompt, and schedule it to run automatically every morning. A briefing that builds itself before you've had coffee. It's the clearest demo of what the non-code surface is for.

    → Claude Cowork: Daily Briefing & Automated Sync (2026) — setup, prompt design, and scheduling.


    Eight deep dives, one hub. Install it, price it, learn the billing and limits, then pick the right surface for the job.

  • Claude vs GPT-5 for Developers: Which API Wins in 2026?

    Claude vs GPT-5 for Developers: Which API Wins in 2026?

    Last refreshed: November 5, 2026

    Update history: August 19, 2026 — first published. October 20, 2026 — Claude figures refreshed (checked October 8, 2026); OpenAI rows carried as October 1 figures, flagged on the page as not re-verified. November 5, 2026 — full rebuild: both vendors verified against current pricing, gpt-6-astra added as OpenAI’s flagship, GPT-5 marked deprecated, legacy context figures corrected. (Later the same day: the two context corrections were themselves reversed — a primary-source read showed Opus 5 and Sonnet 5 carry 1M context; the figures stand as originally published. See the wave-25 log.)

    Claude wins on coding quality and long-context reliability. OpenAI’s deprecated GPT-5 was the cheaper mid-tier list; its current mid-tier matches Sonnet 5.5 on price. Pick the SKU, not the family name.

    Claude figures verified November 5, 2026 against platform.claude.com pricing and Haiku 5.5. OpenAI figures verified November 5, 2026 against current OpenAI pricing; GPT-5 is deprecated and shuts down December 11, 2026.

    The Models Being Compared

    Three cards: coding depth, latency first, agent reliability
    Compare APIs by job shape — not by hype.

    Compare Claude Haiku 5.5 / Sonnet 5.5 / Opus 5.5 against gpt-6-astra / gpt-6.1-sol. GPT-5 remains listed below, deprecated. Fable 5.1 sits above Opus on Anthropic’s list price.

    Model Provider Input (per 1M tokens) Output (per 1M tokens) Context
    Claude Haiku 5.5 (≤100k / >100k) Anthropic $0.10 / $0.50 $0.50 / $2.50 priced by prompt length
    Claude Haiku 4.5 Anthropic $1 $5 still listed
    Claude Sonnet 5.5 Anthropic $2 $10 1M tokens; cache read $0.10
    Claude Sonnet 5 Anthropic $2 $10 1M tokens; cache read $0.20
    Claude Sonnet 4.6 Anthropic $3 $15 1M tokens
    Claude Opus 5.5 Anthropic $4 $20 1M tokens
    Claude Opus 5 / 4.8 Anthropic $5 $25 1M tokens
    Claude Fable 5.1 Anthropic $10 $50 1M tokens
    GPT-5 OpenAI $1.25 $10 400K tokens — deprecated; shuts down December 11, 2026
    gpt-6.1-sol OpenAI $2 $10 prompts over 272K tokens bill at $4 / $15 for the whole request; cache read $0.10
    gpt-6-astra (current flagship) OpenAI $10 $50 cache read $1.00

    Sonnet 5.5 remains $2 / $10, with cache reads at $0.10. Opus 5.5 remains $4 / $20 with cache reads at $0.20. Haiku 5.5 is the new cheap band: $0.10 / $0.50 under 100,000 prompt tokens, $0.50 / $2.50 over. Haiku 4.5 stays $1 / $5. GPT-5’s list ($1.25 / $10) is cheaper per input token than Sonnet 5.5, but GPT-5 is deprecated and shuts down on December 11, 2026. Do not average Haiku 5.5’s two bands.

    Coding Performance

    Use Claude Opus 5.5 or Sonnet 5.5 for interactive coding and agentic runs. Use Haiku 5.5 when the task is a subagent, summary, or classification and the prompt stays under 100k tokens.

    Latency and Context

    Claude Sonnet and Opus SKUs publish a 1M token context window at one rate. Haiku 5.5 raises the rate above 100,000 prompt tokens. Opus 5.5 fast mode is $8 / $40 on the Claude API only.

    Cost Comparison for Real Workloads

    On Claude, cache reads are now 5% of input on Sonnet 5.5 ($0.10) and Opus 5.5 ($0.20), and 2.5% on Fable 5.1 ($0.25). Haiku 5.5 cache reads are $0.01 under 100k. The 50% batch API still applies. For stateless high-frequency calls, Haiku 5.5 under 100k is the Claude list to beat. gpt-6.1-sol short-context matches Sonnet 5.5 at $2 / $10 (verified November 5, 2026); over the 272K band it bills $4 / $15 for the whole request.

    Which API to Choose

    Use Claude for coding, long-context document work, and agentic workflows. Use Haiku 5.5 for the cheap loop. Running both vendors is normal.

    Related: Claude API token rates.