High-performance fable-5-cursor model from Anthropic, featuring 128,000 tokens context window with full OpenAI API compatibility. (Specially optimized variant for Cursor IDE and agentic workflows).
Context Window
128K tokens
Max Output Tokens
64,000 tokens
Release Date
2025 - 2026
Step-by-step Reasoning
Enabled
• Frontier Class• Top Tier• Extended Thinking• Multimodal Vision
$ Token Pricing (Per 1M tokens)
Pay-As-You-Go pricing based on actual usage. No recurring maintenance fees, no minimum commitment, automatic real-time wallet deduction.
Input (Prompt Tokens)
20.165 ₫/M$0.7821/M
250.000 ₫/M$10.00/M92% OFF
Output (Completion Tokens)
20.165 ₫/M$0.7821/M
1.000.000 ₫/M$40.00/M98% OFF
Official provider list price: $10.00 / $40.00 per 1M tokens. Save up to 92% via Gateway.
24h Gateway Performance
Real-world latency and throughput metrics automatically monitored 24/7.
Average TPS
104.3 t/s
Average Latency
14.94 s
Time to First Token
4.28 s
Success Rate
100.00%
Quickstart API Integration
Compatible with standard OpenAI SDKs. Replace the Base URL and pass Model ID fable-5-cursor:
curl https://giahuynexus.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "fable-5-cursor",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, how can you help me today?"}
],
"temperature": 0.7
}'
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://giahuynexus.com/v1"
)
response = client.chat.completions.create(
model="fable-5-cursor",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, how can you help me today?"}
],
temperature=0.7
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const openai = new OpenAI({
apiKey: "YOUR_API_KEY",
baseURL: "https://giahuynexus.com/v1",
});
const response = await openai.chat.completions.create({
model: "fable-5-cursor",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Hello, how can you help me today?" }
],
temperature: 0.7,
});
console.log(response.choices[0].message.content);
fable-5-cursor
fable-5-cursor
Copy the cURL command below and run it in your terminal to test model responses: