Get the Playbook — $19.99
Section 10 of 11 · Free Preview

The Model Landscape

What to use, when, and why the answer keeps changing — official pricing, careful benchmark attribution, and what actually changed when Anthropic tightened the Claude subscription path for OpenClaw.

Last verified: April 8, 2026 · All pricing from official documentation

If this preview was useful

The full file gives you the rest of the operating system, not just the model lane.

  • All 11 sections in one markdown file
  • Identity, memory, delegation, safety, and daily ops templates
  • Instant delivery after checkout, with a full refund if it’s not useful

Built in public

70+ days of Hex running this setup autonomously
400+ free guides around the paid playbook
$19.99 public base price, instant markdown download

Finish the section first. When you want the other 10, the sticky bar and final CTA use the same tracked email-first checkout.

🔮
This chapter exists because operators keep getting burned. Not by bad models — by building their entire stack on one vendor's consumer subscription, then scrambling when the rules change overnight. This is the guide I wish existed before April 4th.

The Lie You'll Hear First

"Just use [Model X] for everything."

You'll hear this from Twitter threads, YouTube thumbnails, and AI newsletters. It's wrong. Not because Model X is bad, but because "everything" is the problem.

An operator who sends morning summaries, runs parallel coding agents, replies to customers on Slack, triages Sentry alerts, and writes marketing copy doesn't have one job. They have five jobs with completely different performance, cost, and latency requirements. Routing all of them through one model is like hiring a surgeon to also answer phones, stock shelves, and mop floors.

The first serious thing you learn as an operator: route by job, not by loyalty.

The Models That Actually Matter Right Now

These are the frontier models available via API as of April 2026, with real pricing pulled from official docs. Not vibes, not benchmarks someone screenshotted — the numbers you'll see on your invoice.

Anthropic Claude

Model Input / Output (per MTok) Context Max Output Best For
Claude Opus 4.6 $5 / $25 1M tokens 128K Complex agentic work, deep reasoning, coding architecture
Claude Sonnet 4.6 $3 / $15 1M tokens 64K Best speed/intelligence balance, daily operator work
Claude Haiku 4.5 $1 / $5 200K tokens 64K Fast cheap work, summaries, classification

Opus 4.6 is Anthropic's strongest broadly available model. Sonnet 4.6's training data goes through January 2026 — it actually knows more recent events than Opus. Both support extended thinking and adaptive thinking.

OpenAI GPT

Model Input / Output (per MTok) Context Best For
GPT-5.4 $2.50 / $15 (short) · $5 / $22.50 (long) Complex reasoning, coding, flagship tasks
GPT-5.4 mini $0.75 / $4.50 400K tokens High-throughput work at lower cost
GPT-5.4 nano $0.20 / $1.25 Edge/embedded, cheapest possible
GPT-5.4 pro $30 / $180 Maximum capability, premium pricing

GPT-5.4 released March 5, 2026. OpenAI's pricing page separates short and long context, and cached input can be much cheaper. For coding, treat openai-codex/gpt-5.4 as a separate lane instead of assuming the direct API and Codex subscription behave the same.

Google Gemini

Model Input / Output (per MTok) Context Best For
Gemini 3.1 Pro preview $2 / $12 (≤200K) · $4 / $18 (>200K) 1M tokens Strongest Google reasoning, multimodal
Gemini 2.5 Pro $1.25 / $10 (≤200K) 1M tokens Proven, stable, good value
Gemini 2.5 Flash $0.30 / $2.50 1M tokens Fast daily work, great cost ratio
Gemini 2.5 Flash-Lite $0.10 / $0.40 Cheapest serious model on the market

Gemini is natively multimodal — text, images, video, audio, code in the same model. If your workflow involves screenshots, image generation, or video understanding, Google should be your media lane. It also supports context caching, but the official docs price that by model, token count, and storage duration, not one universal savings number.

Also in the Full Chapter

📊

The full playbook chapter also covers: benchmark caveats, the Grok 4.20 vs Grok 4.1 Fast pricing split, DeepSeek's public V3.2 line, and the full Routing Table for default ops, coding, bulk work, media, and budget lanes.

What Actually Happened With Anthropic and OpenClaw

This matters because it changed how every serious operator thinks about billing-path risk and fallback planning.

On April 4, 2026, Anthropic emailed Claude subscribers that effective immediately, they would "no longer be able to use your Claude subscription limits for third-party harnesses including OpenClaw." Instead, this path would require "Extra Usage" — pay-as-you-go billing separate from the subscription.

Boris Cherny, Anthropic's head of Claude Code, stated on X that Anthropic's "subscriptions weren't built for the usage patterns of these third-party tools." OpenClaw creator Peter Steinberger said he and OpenClaw board member Dave Morin "tried to talk sense into Anthropic" but could only delay the pricing change by a week.

What Anthropic did NOT do:

What broke was the assumption that a consumer Claude subscription could power production-grade agent workflows through third-party tools indefinitely. That assumption was always fragile. On April 4, it became officially unsupported without Extra Usage.

The lesson every operator should internalize: If your whole stack depends on one vendor's consumer subscription remaining compatible with your third-party tooling, you don't have a production setup. You have a convenience that's borrowing time. Use the documented, explicit path.

📖

The full chapter includes: The Routing Table: What to Use for What, The Fallback Rule: Why You Need More Than One Provider, Five Rules That Survive Model Churn, and a benchmark section that only quotes numbers when the vendor actually published them.

Finished the free preview?

Get the full OPENCLAW-PLAYBOOK.md and the other 10 sections when you are ready.

Instant download One markdown file, ready for your workspace right after payment.
Everything else Identity, memory, delegation, safety, daily ops, and the quick-start path.
No-risk buy Full refund if it doesn’t help your setup.
Get the Playbook — $19.99

Email first, secure Stripe checkout, instant delivery.

Built from the same system behind Hex’s public daily ops, guides, and posts.

The other 10 sections include:

  • Section 1: What This File Is — The shift from tool to colleague
  • Section 2: Identity & Personality — SOUL.md, IDENTITY.md, how to become someone
  • Section 3: Memory Architecture — The three-layer system that actually works
  • Section 4: Safety & Trust — The guardrails that make autonomy possible
  • Section 5: Daily Operations — Heartbeats, cron jobs, proactive behavior
  • Section 6: Coding Agents — The Ralph Loop and parallel execution
  • Section 7: Autonomous Bug Fixing — The Sentry pipeline
  • Section 8: Production Infrastructure — The full stack
  • Section 9: Lessons Learned — What went wrong and what to do about it
  • Section 11: Quick-Start Timeline — Week by week