Skip to main content
Claude Fable 5

Claude Fable 5

Anthropic's most capable widely released model for next-generation intelligence and long-running agents.

1M Context128k OutputAdaptive Thinking

Context Window

1M tokens

Claude Fable 5

Max Output

128k tokens

MTok

Input

$10

Output

$50

Model Codeclaude-fable-5

Playground

claude-fable-5
Reference Images0/5

Click or drag

No output yet

Pricing

PlanContext WindowMax OutputInputOutputCache WriteCache Read
Claude Fable 5
1M tokens128k tokens
$10
$50
5m: $12.50

1h: $20

$1

Claude Fable 5 uses Anthropic's highest-capability Claude API pricing tier.

Prompt caching costs $12.50 per MTok for 5-minute writes, $20 per MTok for 1-hour writes, and $1 per MTok for cache reads.

Batch processing is priced at $5 per MTok for input and $25 per MTok for output.

Developers can access the model via the `claude-fable-5` model code.

Cache read or cached input pricing applies to reused prompt tokens.

README

Claude Fable 5 is Anthropic's most capable widely released model, designed for long-running agents, deep reasoning, complex software engineering, and enterprise work that demands the highest available capability.
  • Claude Fable 5 is Anthropic's highest-capability generally available model, built for long-running agents and difficult work where reasoning quality, sustained execution, and reliability matter more than latency or cost.
  • The model provides a 1M-token context window and 128k-token maximum output. Adaptive thinking is always on, allowing it to allocate reasoning effort dynamically across complex, multi-step tasks.
  • Claude Fable 5 is suited to advanced software engineering, large-scale analysis, deep research, tool-intensive workflows, and enterprise agents that must plan, act, verify, and retain context over extended sessions.

API

Use the API docs for request format, parameters, and integration details.

Anthropic's most capable widely released model for next-generation intelligence and long-running agents.

Model Code

claude-fable-5

View API Docs

API

Endpoint

POST /v1/messages

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/messages" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Introduce ReachAPI in one sentence."
      }
    ],
    "max_tokens": 512,
    "temperature": 0.2
  }'