Claude Fable 5.2 API
Anthropic's newest Fable model, for demanding reasoning and long-horizon agentic work.
claude-fable-5-2Get API keyPricing USD per million tokens
| Tokens | Per 1M tokens |
|---|---|
| Input | $4.48 |
| Cached input | $0.112 |
| Cache write (5 min) | $5.60 |
| Cache write (1 hour) | $8.96 |
| Output | $22.40 |
Reasoning tokens are billed as output. Each answer's usage carries cost_usd, the amount taken from your balance; a request with no answer costs $0.00.
Request
curl https://api.revana.si/v1/chat/completions \
-H "Authorization: Bearer $REVANA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-fable-5-2","messages":[{"role":"user","content":"Write a haiku about routing."}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://api.revana.si/v1", api_key=os.environ["REVANA_API_KEY"])
reply = client.chat.completions.create(
model="claude-fable-5-2",
messages=[{"role": "user", "content": "Write a haiku about routing."}],
)
print(reply.choices[0].message.content)Any OpenAI SDK works: set the base URL to https://api.revana.si/v1. Streaming, tools and the rest are in the chat completions docs.
Details
claude-fable-5-2POST /v1/chat/completions2 routes
Every request starts on the cheapest route. A busy or failed route hands it to the next before any answer is sent.
About the Claude Fable 5.2 API
How much does the Claude Fable 5.2 API cost?
Claude Fable 5.2 costs $4.48 per million input tokens, $0.112 per million cached input tokens and $22.40 per million output tokens on Revana. You pay from prepaid credit for the tokens each request used, with no subscription or minimum.
Is Claude Fable 5.2 cheaper on Revana than on Anthropic?
Yes, 44% or more below the list price. Anthropic lists Claude Fable 5.2 at $8.00 per million input tokens and $40.00 per million output tokens (https://platform.claude.com/docs/en/about-claude/pricing, checked 2026-11-16); Revana charges $4.48 and $22.40 for the same model.
How do I call Claude Fable 5.2 from code?
Use any OpenAI SDK with base URL https://api.revana.si/v1 and your Revana API key, and set model to "claude-fable-5-2". POST /v1/chat/completions takes the OpenAI request body, streamed or not.
What happens if a request fails?
Revana has 2 routes for Claude Fable 5.2 and moves a request to the next one when a route is busy or down. A request that gets no answer costs nothing.
Is Claude Fable 5.2 on Revana the same model?
Yes. Revana passes your request to Anthropic's model unchanged and returns its answer in the OpenAI format, with the usage it reported and what the request cost.
More from Anthropic
Every Claude model and its price
- Claude Fable 5 $5.60 in / $28.00 out per 1M tokens
- Claude Fable 5.1 $5.60 in / $28.00 out per 1M tokens
- Claude Haiku 4.5 $1.44 in / $7.20 out per 1M tokens
- Claude Haiku 4.5 (thinking) $1.44 in / $7.20 out per 1M tokens
- Claude Haiku 5.5 $0.056 in / $0.28 out per 1M tokens
- Claude Opus 4.5 $7.20 in / $36.00 out per 1M tokens
- Claude Opus 4.5 (thinking) $7.20 in / $36.00 out per 1M tokens
- Claude Opus 4.6 $7.20 in / $14.40 out per 1M tokens
Also as markdown for agents. Every language model and price: llms.json.