Anthropic: Claude Fable 5

anthropic/claude-fable-5

Claude Fable 5 is a previous-generation Anthropic flagship that still ranks #5 of 235 on the TryAii Score — now 3.8 points behind Claude Fable 5.1 at the same $50-per-million-output price. It remains strongest on coding (#2 on SciCode). It costs $10/$50 per million input/output tokens, while comparable scores now sell for around $6 per million output tokens elsewhere.

Prompt $/1M

$10.000

Completion $/1M

$50.000

Context

1,000,000 tok

Best provider

67 tok/s · Artificial Analysis

Specs

Model id: anthropic/claude-fable-5
Display name: Anthropic: Claude Fable 5
Modality: text+image+file->text
Tokenizer: Claude
Instruct type: —
Context length: 1,000,000
Max completion: 128,000
Prompt $/1M: $10.000
Completion $/1M: $50.000
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedyes

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Artificial Analysis	67	68,044 ms	—
Googlefastest	48	4,062 ms	4,414 ms
Anthropic	43	5,424 ms	6,137 ms
Amazon Bedrock	36	7,997 ms	9,099 ms
Azure	11	5,425 ms	5,883 ms
Claude Platform on AWS	5	2,930 ms	4,093 ms
anthropicfastest	—	—	—

Prompt caching by provider

Provider	Min tokens to cache	Notes
Anthropic	512 tokens	Fable 5 / Opus 5 tier — lowest Anthropic floor (Opus 5 halved from Opus 4.8's 1,024). Explicit cache_control breakpoints required; 5-min TTL refreshed free on every hit; 1h TTL opt-in at 2x write premium.
Google Vertex	512 tokens	Claude-on-Vertex, Fable 5 / Opus 5 tier: cache_control breakpoints exactly as on the direct API; per-model Anthropic tiers apply.
Amazon Bedrock	1,024 tokens	Fable 5 / Opus 5 on Bedrock: 1,024 assumed conservatively (512 on the direct API; Anthropic docs defer to AWS and the AWS side is unverified as of 2026-08).