Enterprise Plans
AI Application Development
AI Translator API
AI SEO/GEO Service
Web Scraping Service
Log in
const { OpenAI } = require('openai');
const api = new OpenAI({
baseURL: 'https://api.ai.cc/v1',
apiKey: '',
});
const main = async () => {
const result = await api.chat.completions.create({
model: 'openai/gpt-oss-120b',
messages: [
{
role: 'system',
content: 'You are an AI assistant who knows everything.',
},
{
role: 'user',
content: 'Tell me, why is the sky blue?'
}
],
});
const message = result.choices[0].message.content;
console.log(`Assistant: ${message}`);
};
main();
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.ai.cc/v1",
api_key="",
)
response = client.chat.completions.create(
model="openai/gpt-oss-120b",
messages=[
{
"role": "system",
"content": "You are an AI assistant who knows everything.",
},
{
"role": "user",
"content": "Tell me, why is the sky blue?"
},
],
)
message = response.choices[0].message.content
print(f"Assistant: {message}")
-
AI Playground
Test all API models in the sandbox environment before you integrate.
We provide more than 300 models to integrate into your app.
.avif)
Product Detail
GPT OSS 120B is a cutting-edge, large-scale open-source language model engineered for high-capacity reasoning, advanced coding, and a wide array of general-purpose tasks. It adeptly balances the state-of-the-art performance expected from 100+ billion parameter models with remarkable cost efficiency, democratizing access for researchers and developers. GPT OSS 120B excels in diverse applications, from text generation and multi-step logical reasoning to comprehensive multilingual understanding.
⚙️Technical Specifications
- Robust Performance: Achieves accuracy comparable to top-tier GPT models in reasoning benchmarks.
- Coding Prowess: Highly competitive in academic and industry coding challenges against other large foundation models.
- Versatile Reasoning: Strong multi-domain reasoning, including STEM, natural language understanding, and complex dialogue.
Performance Benchmarks
- Model Size: 120 billion parameters
- Context Window: 128K tokens
API Pricing
- Input tokens: $0.04431 per million tokens
- Output tokens: $0.4431 per million tokens
💡Key Capabilities
- Advanced Reasoning: Employs chain-of-thought and hybrid inference modes for efficient, multi-step problem solving.
- Multimodal Input Support: Natively processes text and image inputs for rich contextual understanding (planned or available).
- Tool Integration: Supports external tool usage (e.g., Python execution, web browsing, API calls) for autonomous workflows.
- Code Generation: Generates and edits code across multiple languages with near expert-level performance.
- Scalable Context: Extended context length efficiently handles large documents, codebases, and long conversations.
🎯Optimal Use Cases
- Large-scale Document Analysis: Ideal for synthesizing vast amounts of information.
- Software Development: Advanced assistance for complex coding and debugging.
- Deep Research: Supports projects requiring deep reasoning and multi-step workflows.
- Multimodal AI Applications: Excellent for tasks involving both textual and visual data.
- Cost-Aware Deployments: High model capacity with relative cost efficiency for various applications.
💻Code Sample
🆚Comparison with Other Models
vs GPT-4o Mini: GPT OSS 120B features a significantly larger parameter count, excelling in high-capacity reasoning and code generation. In contrast, GPT-4o Mini is designed for smaller, more cost-efficient operations with built-in multimodal support for text and images.
vs GLM-4.5: While GLM-4.5 boasts more total and active parameters, leading in advanced tool integration and agentic task performance, GPT OSS 120B remains highly competitive with strong reasoning benchmarks and greater efficiency on smaller hardware footprints.
🚧Limitations and Considerations
- Cost: Reflects its advanced capabilities and scale, leading to higher costs compared to smaller models.
- Prompt Design: Optimal performance in highly creative or open-ended tasks requires explicit prompt engineering.
- Latency & Throughput: Dependent on input size and model load; larger contexts will incur longer processing times.
❓Frequently Asked Questions (FAQ)
What is GPT OSS 120B?
GPT OSS 120B is a large-scale, open-source language model designed for advanced reasoning, coding, and general-purpose AI tasks, balancing high performance with cost efficiency.
What are the key capabilities of GPT OSS 120B?
Its key capabilities include advanced reasoning with multi-step problem-solving, planned multimodal input support (text and image), external tool integration, expert-level code generation, and scalable context handling for large documents and conversations.
How does GPT OSS 120B compare to other models like GPT-4o Mini?
GPT OSS 120B offers a significantly larger parameter count (120B) and excels in complex reasoning and code generation, while GPT-4o Mini is smaller, more cost-efficient, and features built-in multimodal support.
What are the API pricing details for GPT OSS 120B?
API pricing is set at $0.04431 per million input tokens and $0.4431 per million output tokens.
What are the main limitations of GPT OSS 120B?
Limitations include higher costs reflecting its advanced scale, the need for explicit prompt design in highly creative tasks, and latency/throughput variations based on input size and model load.
Learn how you can transformyour company with AICC APIs
