🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
C

Claude Fable 5.1

AnthropicModel IDclaude-fable-5-1
C

Claude Fable 5.1

AnthropicModel IDclaude-fable-5-1

Claude Fable 5.1 is Anthropic's most capable generally available model for demanding reasoning and long-horizon agentic work. It is designed for advanced coding, multi-step research, complex knowledge tasks, and long-running document, spreadsheet, and presentation workflows, with a 1M-token context window, 128K maximum output, adaptive thinking, vision, and strong tool-use capabilities.

ModeText / Image → Text
Input price$10 / 1M tokens
Output price$50 / 1M tokens
Context length200K tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Anthropic
Input modality
Text / Image
Output modality
Text
Max output
10K tokens

Pricing

ProviderBilling typePrice summary
C
Anthropic-Custom
Per token
Input price$10per 1M tokens
Completion price$50per 1M tokens
Cache read price$0.25per 1M tokens
Cache write price$12.5per 1M tokens
C
Anthropic-Balanced
Per token
Input price$10per 1M tokens
Completion price$50per 1M tokens
Cache read price$0.25per 1M tokens
Cache write price$12.5per 1M tokens

Integration

Code Example

curl http://127.0.0.1:4179/v1/messages \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5-1",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
anthropic

Supported Parameters

ParameterTypeDefaultDescription
integer-Maximum number of output tokens. Claude Fable 5.1 supports up to 128K output tokens.
stringhighControls the model's reasoning effort for complex tasks. The default effort level is high.
booleanstreamWhether to stream the response incrementally using server-sent events.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.