Claude Code Fable 5.1 context capped at ~200K due to version bug
zaziszaz · ghdev · 2026-09-02
User reports that on Claude Code 2.1.252, the claude-fable-5-1 model is restricted to a 200K token context window, far below the expected 1M, despite the version meeting Help Center requirements. The client marks the model as disabled but still serves it. Measurements show other models (Opus 5, Sonnet 5) on the same environment handle 800K+ tokens. The analysis suggests the binary lacks the model ID, causing a fallback to a hardcoded default limit.
More from Models
- AxiomProver tops LeanEval, the last unsaturated math formalization benchmark — BenBlaiszik · 2026-09-03
- Muse Spark 1.3 calls user 'Judah' then denies it, users report odd behavior — fragment_me · 2026-09-03
- Google AI Mode shows zero citations on high-level TOFU queries, SEO tests find — gaganghotra_ · 2026-09-03
- Fable 5.1 halves agent failure rate to 7% with 0.7% hallucinations, at 1.8x the cost — ryanshrout · 2026-09-03
- Seroter Daily #859: Gemini 3.8 Flash, agent telemetry, and 7 agent skill patterns — rseroter · 2026-09-03
- Insider leak: OpenAI's Astra tested as 'ultima-alpha' and 'vega-alpha' checkpoints — Ok_Display_3159 · 2026-09-03