Claude Fable 5 API
Anthropic's most capable widely available model. Top of most frontier leaderboards with a 1M context window — built for long-running autonomous agents and research-grade work.
💰 Save up to 70% vs official Anthropic pricingClaude Fable 5 — cheaper than the official Anthropic API
Access Claude Fable 5 through AI API Hub and pay less per token. Same OpenAI-compatible endpoint, lower cost.
Technical Specifications
| Provider | Anthropic |
| Model Family | Claude Fable 5 |
| Release Date | 2026-06 |
| Context Window | 1M |
| Max Output Tokens | 131,072 |
| Input Price | $10.00 / 1M tokens |
| Output Price | $50.00 / 1M tokens |
| Vision Support | Yes ✓ |
| Function Calling | Yes ✓ |
| JSON Mode | No |
| Streaming | Yes ✓ |
| Fine Tuning | Not Available |
| Status | Active ✓ |
Overview
Claude Fable 5 is Anthropic's current mythos model, released in 2026-06. Anthropic's most capable widely available model. Top of most frontier leaderboards with a 1M context window — built for long-running autonomous agents and research-grade work.
For developers, the headline numbers are a 1M context window and up to 131,072 output tokens per response — enough headroom for most capable claude and long-running agents without chunking your input. Priced at $10.00/1M input and $50.00/1M output, it sits in the premium tier — best reserved for tasks where quality justifies the spend.
On the capability side, Claude Fable 5 exposes 4 features: Vision, Tool Use, Adaptive Thinking, Streaming. Note that fine-tuning isn't supported — you'll work with the base model. Vision support means you can pass images alongside text, handy for document parsing or UI automation.
The practical appeal of routing Claude Fable 5 through AI API Hub is simplicity: one OpenAI-compatible endpoint, USDT & USDC payments, no credit card, and you're calling the API in under 30 seconds — just swap your base URL.
What Makes Claude Fable 5 Different
How Claude Fable 5 is used
Claude Fable 5 is used for agentic workflows combining visual understanding with action — document processing pipelines that extract data and call APIs, visual Q&A systems, and multimodal agents. Tool calling enables it to trigger external functions based on what it sees in images.
Pricing position within Anthropic
Claude Fable 5 is the most expensive active model from Anthropic at $10.00/1M input — the premium tier. The cheapest sibling costs $1.00/1M (90% less). Reserve Claude Fable 5 for tasks where its capabilities justify the premium; route bulk traffic to cheaper siblings.
Claude Fable 5's role in the lineup
Within Anthropic's lineup, Claude Fable 5 is the flagship — the most capable and most expensive option. It's part of the mythos family (2 active variants share this family). Use it when quality matters more than cost; switch to a cheaper sibling for high-volume or less demanding tasks.
Real-world use cases
Real-world deployments: document processing pipelines (read invoice → extract fields → call accounting API), visual Q&A systems, and multimodal agents that act on what they see. Claude Fable 5 handles the full see-decide-act loop in a single model call.
vs sibling models
What makes Claude Fable 5 different from sibling models: compared to Claude Mythos 5 ($0.00/1M cheaper, same 1M context); Claude Opus 5 ($5.00/1M cheaper, same 1M context); Claude Sonnet 5 ($7.00/1M cheaper, same 1M context). Choose Claude Fable 5 when vision input is needed.
API Examples
Python
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.apiyihe.org/v1"
)
response = client.chat.completions.create(
model="claude-fable-5",
messages=[
{"role": "user", "content": "Hello"}
]
)
print(response.choices[0].message.content)JavaScript / Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.API_KEY,
baseURL: "https://api.apiyihe.org/v1"
});
const response = await client.chat.completions.create({
model: "claude-fable-5",
messages: [
{ role: "user", content: "Hello" }
]
});
console.log(response.choices[0].message.content);cURL
curl https://api.apiyihe.org/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "claude-fable-5",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Supported Features
| Vision / Image Input | ✅ Supported |
| Audio / Voice Input | ❌ Not Available |
| Function Calling | ✅ Supported |
| JSON Mode | ❌ Not Available |
| Streaming | ✅ Supported |
| Fine-Tuning | ❌ Not Available |
| Multimodal | ❌ Not Available |
Benchmark Scores
| Benchmark | Score |
|---|---|
| MMLU | Not Publicly Available |
| GPQA | Not Publicly Available |
| SWE-Bench | Not Publicly Available |
| HumanEval | Not Publicly Available |
| GSM8K | Not Publicly Available |
| MATH | Not Publicly Available |
| MMMU | Not Publicly Available |
Pricing History
Claude Fable 5 was released in 2026-06 by Anthropic and is currently publicly available via AI API Hub.
Current Pricing: $10.00 per 1M input tokens · $50.00 per 1M output tokens. Pay-as-you-go with no minimum commitment.
Pricing Model: Token-based billing (pay per use). No subscription fees. No hidden costs.
💡 Anthropic occasionally updates pricing. AI API Hub reflects current pricing in real-time. All prices in USD. Pay with USDT or USDC — no currency conversion fees.
Compare Alternatives
Frequently Asked Questions
What is Claude Fable 5?
Claude Fable 5 is Anthropic's current mythos model. Anthropic's most capable widely available model. Top of most frontier leaderboards with a 1M context window — built for long-running autonomous agents and research-grade work. It offers a 1M context window and supports Vision, Tool Use, Adaptive Thinking. You can access it through AI API Hub using USDT or USDC — no credit card required.
How much does Claude Fable 5 cost?
Claude Fable 5 is priced at $10.00 per 1M input tokens and $50.00 per 1M output tokens, billed pay-as-you-go with no minimum. Through AI API Hub you can start with as little as $5 and scale from there.
Claude Fable 5 vs GPT-5.6 Sol?
They're built for different jobs. Claude Fable 5 costs $10.00/1M input with a 1M window; GPT-5.6 Sol runs $5.00/1M input with 1M. GPT-5.6 Sol is the cheaper option, while Claude Fable 5 trades cost for most capable claude. See the full side-by-side at /compare/claude-fable-5-vs-gpt-5.6-sol/.
Claude Fable 5 context window?
Claude Fable 5 has a 1M context window, capable of processing up to 1,048,576 tokens in a single request. Maximum output tokens: 131,072.
Does Claude Fable 5 support function calling?
Yes, Claude Fable 5 supports function/tool calling, allowing you to define functions that the model can invoke. This enables AI agents, API integrations, and structured data extraction.
Is Claude Fable 5 multimodal?
Partially — Claude Fable 5 supports vision (image input) but not native audio processing.
Claude Fable 5 API rate limits?
Claude Fable 5 rate limits: 1K RPM. Higher tier plans offer increased throughput. For high-volume production use, consider Anthropic's faster variant models.
How to access Claude Fable 5 API?
Access Claude Fable 5 through AI API Hub: (1) Register at api.apiyihe.org/register?aff=8JZC, (2) Deposit USDT/USDC, (3) Get your API key instantly, (4) Use the OpenAI-compatible endpoint https://api.apiyihe.org/v1 with model name "claude-fable-5". Start building in under 30 seconds.