Claude Fable 5.2 API pricing
Claude Fable 5.2, often written Fable 5.2: $4.00 in, $20.00 out per million tokens, 50% under Anthropic's list price.
Price · per million tokens, USD
Get a key| Tokens | Anthropic list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | $8.00 | $4.00 | -50% |
| Cached input | $0.20 | $0.10 | -50% |
| Output | $40.00 | $20.00 | -50% |
Claude Fable 5.2 vs Claude Fable 5.1 price · per million tokens, USD
Claude Fable 5.1| Tokens | Claude Fable 5.1 | Claude Fable 5.2 | List change |
|---|---|---|---|
| Input | $6.00list $10.00 | $4.00list $8.00 | -20% |
| Cached input | $2.00list $0.25 | $0.10list $0.20 | -20% |
| Output | $30.00list $50.00 | $20.00list $40.00 | -20% |
Claude Fable 5.2 specs
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- text and image
- Released
- November 9, 2026
What is Claude Fable 5.2? · what Anthropic has said, dated
Claude Fable 5.2 is Anthropic's latest Fable model, released on 2026-11-09 for demanding reasoning and long-horizon agentic work. It has a 1M-token context window, 128K max output and a June 2026 knowledge cutoff, and Anthropic lists it as active with retirement not sooner than 2027-11-09 (Fable 5.2 reference, read 2026-11-09).
Anthropic's list price is $8.00 input and $40.00 output per million tokens; Claude Fable 5.1 lists at $10.00 input and $50.00 output per million tokens (Anthropic pricing, read 2026-11-09).
Here claude-fable-5.2 is served at $4.00 input and $20.00 output per million tokens, live from the catalog, and the daily real-model check shows whether the model answering is unchanged.
Claude Fable 5.2 API key · base URL and setup
- Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
- Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
- Send claude-fable-5.2 as the model. The same key calls every other model in the catalog.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="claude-fable-5.2",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'claude-fable-5.2',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"claude-fable-5.2","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.