Claude Fable 5

LLM Provider / Model · Long-running autonomous agents, the hardest reasoning and long-horizon engineering work

At a glance

Input price	$10
Output price	$50
Cache price	$1
Price tier	Premium
Context window	1M+
Max output	128K
Context tier	500K+
Speed tier	Slow/Reasoning
Latency	high
Knowledge cutoff	Jan 2026
Modality	Multimodal (vision)
Model ID	claude-fable-5
Provider	Anthropic
Benchmark	Anthropic’s most capable widely released model
Released	Jun 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Always-on adaptive thinking, Effort control (low-max), Streaming, Structured output, Prompt caching, Task budgets, Compaction

Vision, Tool use, Always-on adaptive thinking, Effort control (low-max), Streaming, Structured output, Prompt caching, Task budgets, Compaction

Long-running autonomous agents, the hardest reasoning and long-horizon engineering work

Trae's built-in model menu may not include Claude Fable 5 — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models — Claude Fable 5 is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is Claude Fable 5.
Devin uses Cognition's proprietary model internally — your selected Claude Fable 5 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Claude Fable 5 will be ignored.
Jules runs Gemini models internally — your selected Claude Fable 5 will be ignored.
Lovable uses a fixed internal model — your selected Claude Fable 5 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Claude Fable 5 will be ignored.

Build a full stack around Claude Fable 5 — Flowpicker shows compatibility warnings before you commit.