FABLE 5

Claude Code v2.1.257 points /model fable at Fable 5.1: 1M context, $10/$50 per MTok, $0.25 cache reads. Setup, gotchas, and when Opus 5.5 wins.

Anthropic retuned Claude Fable 5 biology safeguards, cutting biology fallbacks about 85%. What changed and what still routes to Opus 5.

Anthropic removed over 80% of Claude Code's system prompt for Claude 5 models. Here is how the rules changed and what it means for your CLAUDE.md files, skills, and system prompts.

Claude Opus 5 launched July 24, 2026 at $5/$25 per MTok - matching Opus 4.8 pricing while delivering near-Fable 5 intelligence. Full benchmark comparison across 7 evals, pricing breakdown, and decision guide.

Claude Fable 5 found a counterexample to the 87-year-old Jacobian conjecture, and Terence Tao worked through the math. How it works and what HN is saying.

Claude Fable 5 in 7 minutes: a companion guide to the video review covering benchmarks, pricing, availability, demos and hands-on developer takeaways.

Agent fleet economics: one Fable 5 orchestrator plus Sonnet 5 workers beats an all-frontier fleet for most work. The cost math and the tokenizer caveat.

Fable 5 agent orchestration with the manager-model pattern: a 1M-context orchestrator that delegates to cheaper workers via fan-out, pipelines and verify loops.

Fable 5 agent fleet operations: 30-day retention limits, refusal-rate alerting, per-role effort tuning, observability and availability planning for production.

Fable 5 is back after a US export-control suspension. What the Anthropic model is, the specs and refusal behavior to handle, and when to pick Opus 4.8.

Run Fable 5 agents on Vercel eve: wire durable sessions, Sandbox code execution, approvals and subagents to a long-horizon model, with honest costs and fit.

Fable 5 vs Opus 4.8 as your agent fleet orchestrator: a fair head-to-head with a decision matrix by run length, budget, compliance and refusal tolerance.

Fable 5 refusals return a 200 with stop_reason refusal, not an error. Detect them in every worker, fall back to Opus 4.8 and track refusal rate as a metric.

Long-horizon agents on Fable 5: what 1M context, 128K output, the memory tool, compaction and task budgets unlock, what is verified, and six projects to try.

Claude Fable 5 and Mythos 5 were suspended for all users by a US export control directive. What it said, why it hit everyone, and what changed for developers.

Claude Mythos 5 vs Fable 5 explained. They are the same underlying model with different access and safeguards, which is why both were suspended together.

Is Claude Fable 5 down? It was suspended on June 12, 2026 by a US export directive, not an outage. What to use instead, and the update on its return.

Fable 5 was pulled by a US export control directive, disabling it and Mythos 5 for every customer. What happened, what still works, and what to do next.

Model dependency risk after Fable 5 was pulled overnight. A playbook for one-model stacks - abstract the model layer, test fallbacks, keep an open-weight floor.

A narrow jailbreak that other models can match does not get a frontier model recalled. So what actually happened? The plausible explanations, ranked.