API pricing per million tokens
- Input
- $10
- per 1M, list
- Output
- $50
- per 1M tokens
- Cached input
- $0.25
- batch $5 / $25
- Context
- 1M
- 128K max output
Where to buy it (4)
AWS Bedrockdefault region$10 / $50cached $0.25
Azure AI Foundrydefault region$10 / $50cached $0.25
Google Vertex AIglobal$10 / $50cached $0.25
Anthropic (list)the lab's own API$10 / $50cached $0.25
Through a gateway
Your own numbers100M input and 20M output tokens a month: $2,000 direct.
Helicone$2,000+0%
Kong AI Gateway$2,000+0%
LiteLLM$2,000+0%
Vercel AI Gateway$2,000+0%
Databricks Mosaic AI$2,000+0%
Hugging Face Inference$2,000+0%
Cloudflare AI Gateway$2,100+5%
Requesty$2,100+5%
Eden AI$2,110+5.5%
OpenRouter$2,110+5.5%
Snowflake Cortex AI$2,400+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
GPT-6 AstraOpenAI · 1.05M$10 / $50in / out per 1M$10$50$11.05MSep 4, 2026
About Claude Fable 5.1
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
Takes text, image, files in and returns text. First listed Sep 2, 2026. Blended price $20 per 1M tokens at 3 input to 1 output. Overall score 58 on leadersboard.fru.dev (rank 1).
Questions
How much does Claude Fable 5.1 cost?
$10 per million input tokens and $50 per million output tokens, with cached input at $0.25, or $5 and $25 through the Batch API.
What is the context window of Claude Fable 5.1?
1M tokens, with up to 128K tokens of output.
Where is Claude Fable 5.1 cheapest?
Of 4 routes tracked, AWS Bedrock is cheapest at $10 input and $50 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.