GPU/Deploy AI Models/GPT OSS 120B
Enterprise LLM

GPT OSS 120B

Large-scale open-source GPT model with 120 billion parameters. Enterprise-grade performance for chatbots, content generation, and code assistance under Apache 2.0 license.

Model Specifications

Parameters120 Billion
ArchitectureTransformer (GPT)
Context Length8,192 tokens
Training DataWeb + Books + Code
LanguagesEnglish + 50+ languages
LicenseApache 2.0

Pricing Options

Serverless API

Pay per token with auto-scaling

₹80 input /1M tokens
₹160 output /1M tokens
  • Auto-scaling
  • No minimum
  • 99.9% uptime
  • Rate limits apply
Recommended

Dedicated Instance

Reserved GPU for consistent performance

₹500/hour
  • 4x H100 GPUs
  • No rate limits
  • Fine-tuning support
  • Private deployment

Recommended Hardware

GPU configurations for running GPT OSS 120B.

4x

NVIDIA H100

320 GB total

Recommended for production

8x

NVIDIA A100

640 GB total

Cost-effective alternative

Use Cases

Enterprise Chatbots

Build intelligent conversational agents for customer support.

Content Generation

Generate high-quality articles, marketing copy, and creative content.

Code Assistance

Help developers write, review, and debug code.

Document Analysis

Extract insights and summaries from large documents.

Quick Start

curl https://api.host360.cloud/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [
      {"role": "user", "content": "Explain quantum computing"}
    ]
  }'

Ready to Deploy GPT OSS 120B?

Start with our serverless API or deploy on dedicated GPUs.