Skip to content

gpt-oss-120b · Incognito

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.

Pricing

Input
$0.1575per 1M tokens
Output
$0.63per 1M tokens
Max output
32,768tokens

Phala's price plus a 5% routing fee. Deference adds no markup.

~/.codex/config.toml

model = "openai/gpt-oss-120b:incognito"
model_provider = "deference"
web_search = "disabled"

[model_providers.deference]
name = "Deference"
base_url = "https://deference.si/v1"
wire_api = "responses"
env_key = "DEFERENCE_API_KEY"
Codex, set up for gpt-oss-120b · Incognito