openai/gpt-oss-120bOpen WeightsOpen GPT reasoning model for self-hosted agents and controllable deployments
TECHNICAL SPECIFICATIONS
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ GPT OSS 120B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.
MCP Context Window Recommendations
With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.
API CALL INVOCATION EXAMPLE
// Example: Calling GPT OSS 120B via OpenAI SDK
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPENAI_API_KEY,
});
const response = await client.chat.completions.create({
model: "openai/gpt-oss-120b",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
This model supports prompt caching at $0.01 / 1M tokens, saving up to 89% on repetitive MCP tool definitions and system instructions.
MODEL RESOURCES
More Models by OpenAI
Alternative and family models from the same lab
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
More exact GPT-5.4 tier for demanding professional reasoning and agent tasks
Balanced GPT-5.6 model for capable, cost-efficient everyday work