OpenAI

GPT-OSS 120B

OpenAI's first open-weight model since GPT-2. Mixture-of-experts 120B with strong general reasoning at a price that's hard to beat.

120B (MoE, ~5B active)Apache 2.0

Context

131.072k

Tokens / sec

TTFT

240ms

Hardware

AWS Trainium

Pricing

Input: $0.04 / 1M tokens
Output: $0.18 / 1M tokens
Context cache: 50% of input rate, automatic
Fine-tunes: Same per-token price as base

Capabilities

SSE streaming
Tool / function calling
Structured JSON outputs

Use cases

General chatCodingReasoningTool use

Quickstart

Full quickstart

gpt-oss-120b.py

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cogito.decart.ai/v1",
    api_key=os.environ["COGITO_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)