Short answer
Claude Fable 5.2 is available through APIVAI at $3.18 per million input tokens and $15.90 per million output tokens as of 2026-11-10, 60% below Anthropic's official list price of $8.00 / $40.00. Use the model ID claude-fable-5-2 with an APIVAI key in the Anthropic Messages format at https://api.apivai.com (Claude Code, Anthropic SDK) or the OpenAI format at https://api.apivai.com/v1. Billing is pay-as-you-go from a prepaid balance, from $10, with no subscription.
Claude Fable 5.2 API pricing
| Per 1M tokens | APIVAI | Official list price |
|---|---|---|
| Input | $3.18 | $8.00 |
| Output | $15.90 | $40.00 |
Prompt caching: cache writes cost $3.97 and cache reads $0.08 per million tokens. Context window: 1M tokens. Prices are checked against the price list every 6 hours; see all model prices.
Anthropic describes each model's abilities and limits in its model documentation.
How much does Claude Fable 5.2 cost per request?
Each request is billed for its input and output tokens. Coding agents resend the conversation and files with every step, so their requests are much larger than a chat message.
| Example | Input / output tokens | APIVAI | Official price |
|---|---|---|---|
| One chat message | 2,000 / 500 each | $0.0143 | $0.036 |
| One coding-agent step | 30,000 / 1,500 each | $0.119 | $0.30 |
| 1,000 chat messages | 2,000 / 500 each | $14.31 | $36.00 |
| A month of agent use (100 steps a day, 22 days) | 30,000 / 1,500 each | $262 | $660 |
| One coding-agent step with prompt caching (25,000 of the 30,000 input tokens read from cache) | 30,000 / 1,500, 25,000 cached | $0.0418 | — |
Thinking and reasoning tokens are billed as output, so when the model thinks, the output count can be higher than the text you see.
To price your own workload, use the cost calculator; to choose between models, see Sonnet vs Opus vs GPT: API cost compared; for how this compares with buying from Anthropic directly, see APIVAI vs the Anthropic API.
How do you call Claude Fable 5.2?
cURL (OpenAI format)
curl https://api.apivai.com/v1/chat/completions \
-H "Authorization: Bearer $APIVAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-fable-5-2",
"max_tokens": 4096,
"messages": [{"role": "user", "content": "Hello!"}]
}'Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(api_key="YOUR_APIVAI_API_KEY", base_url="https://api.apivai.com/v1")
resp = client.chat.completions.create(
model="claude-fable-5-2",
max_tokens=4096,
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Claude Code and the Anthropic SDK
# macOS / Linux export ANTHROPIC_BASE_URL="https://api.apivai.com" export ANTHROPIC_AUTH_TOKEN="YOUR_APIVAI_API_KEY" claude --model claude-fable-5-2
# Python (Anthropic SDK)
import anthropic
client = anthropic.Anthropic(api_key="YOUR_APIVAI_API_KEY", base_url="https://api.apivai.com")
msg = client.messages.create(model="claude-fable-5-2", max_tokens=4096,
messages=[{"role": "user", "content": "Hello!"}])Claude Code and the Anthropic SDK use https://api.apivai.com without /v1; they add /v1/messages themselves. If ANTHROPIC_API_KEY is set in your shell, remove it first. Full setup: Claude Code guide and Claude API proxy.
Other Anthropic models
| Model | Input / output per 1M | Below official price |
|---|---|---|
| Claude Fable 5.1 | $3.97 / $19.87 | 60% |
| Claude Fable 5 | $3.97 / $19.87 | 60% |
| Claude Opus 5 | $1.89 / $9.47 | 62% |
| Claude Opus 4.8 | $1.89 / $9.47 | 62% |
| Claude Opus 4.7 | $1.89 / $9.47 | 62% |
| Claude Opus 4.6 | $1.89 / $9.47 | 62% |
| Claude Opus 5.5 | $1.52 / $7.57 | 62% |
| Claude Sonnet 4.6 | $1.14 / $5.68 | 62% |
| Claude Sonnet 5.5 | $0.75 / $3.79 | 63% |
| Claude Sonnet 5 | $0.75 / $3.79 | 63% |
| Claude Haiku 4.5 | $0.38 / $1.89 | 62% |
| Claude Haiku 5.5 | $0.19 / $0.94 | — |
Setup guides
- Claude Code Custom API Setup: Base URL and API Key Guide
- Cline Setup with Claude and GPT via a Custom API Key
- Roo Code Setup with Claude and GPT via a Custom API Key
- Continue.dev with Claude and GPT: Custom API in config.yaml
- Cherry Studio Setup: Use Claude and GPT via a Custom API
- Dify with Claude and GPT via an OpenAI-Compatible API
- Claude API Pricing 2026: Official Rates and Cache Prices
- Claude Code Without a Subscription: Pay Per Token Instead
- Claude API Without a Credit Card: Alipay, WeChat Pay, USDT
- Is Your Claude API Relay Serving the Real Model? How to Check
FAQ
Is this the same Claude Fable 5.2 model?
Yes. Requests with the model ID claude-fable-5-2 are answered by Claude Fable 5.2; only the price and the way you pay differ. You can check that requests reach Anthropic's Claude with the thinking-signature test: an unchanged signature is accepted and an altered one is rejected. We ran it on 2026-10-19 on Claude Haiku 4.5 and Claude Sonnet 4.6 with exactly that result. The test shows the backend is Anthropic's Claude, not which Claude model answered; the method and script are in Is your Claude API relay serving the real model?, and you can run it on any model yourself.
What is the model ID for Claude Fable 5.2?
claude-fable-5-2. The list of models changes over time, so check GET https://api.apivai.com/v1/models with your key before hard-coding a name.
Which tools can use Claude Fable 5.2?
Claude Code and the Anthropic SDK through https://api.apivai.com, and any OpenAI-compatible tool (Cursor, Cline, Continue, Aider and others) through https://api.apivai.com/v1.
How is Claude Fable 5.2 billed?
Per token, from a prepaid balance: $3.18 per million input tokens and $15.90 per million output tokens, with thinking tokens counted as output. The minimum top-up is $10 by card or crypto, or ¥20 by Alipay or WeChat Pay, and there is no subscription.
How many requests can I send?
Each key allows 60 requests per minute; each key has its own limit, so use several keys for more.
Create an account, top up from $10 and use claude-fable-5-2 with your key.