No description available
Fable 5.2 APIActive
AI Code With channel availability
The same model is billed by channel discount. Copy a channel code to set your preference.
Related Models
More models from Anthropic
Compare models from other providers
Fable 5.2 API: price, model ID, and how to call it
Call Fable 5.2 through AI Code With. Use model ID claude-fable-5-2 with 1M context. list price about $8.00 / $40.00 per 1M tokens before channel discounts. About $0.4680 for 100,000 input / 10,000 output tokens at the cheapest live channel.
Next: Get API key · Claude Code setup guide · Compare Claude models · All model prices
Cost calculator
Estimate at the cheapest live channel: $3.12 / $15.60 per 1M tokens, cache read $0.0780, cache write $3.90. Billed usage follows your prepaid balance.
cURL example
Set model to claude-fable-5-2. The page slug is only the URL, not the API parameter.
curl https://api.aicodewith.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $AICODEWITH_API_KEY" \
-d '{
"model": "claude-fable-5-2",
"messages": [
{ "role": "user", "content": "What is the meaning of life?" }
]
}'FAQ
What is the Fable 5.2 model ID?
Send model "claude-fable-5-2" in the API request. The page path /claude-fable-5-2 is only the URL, not the model parameter.
How do I call the Fable 5.2 API?
Use one AI Code With API key against https://api.aicodewith.ai/v1/chat/completions(OpenAI Chat Completions)和 https://api.aicodewith.ai/v1/messages(Anthropic Messages,Authorization: Bearer), and set model to claude-fable-5-2. Supported protocols: OpenAI Chat Completions / Anthropic Messages. See Claude Code setup guide.
How is Fable 5.2 priced?
Fable 5.2 is list price about $8.00 / $40.00 per 1M tokens before channel discounts. The public page shows available channel discounts; billed usage follows your prepaid balance and the live channel. About $0.4680 for 100,000 input / 10,000 output tokens at the cheapest live channel.
How long is the Fable 5.2 context window?
Fable 5.2 has about 1M input context and up to 128K output tokens. Treat that as capacity, not a reason to fill every request.
GPT-5.6 Sol