OpenAI GPT OSS 120B API: Pricing and Specs

OpenAI GPT OSS 120B API

OpenAI GPT OSS 120B is a large language model by OpenAI, available on the Venice API as openai-gpt-oss-120b. Private and end-to-end encrypted variants are available.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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation

OpenAI GPT OSS 120B API pricing

Model ID	Variant	Privacy	Price
`openai-gpt-oss-120b`	Standard	Private	$0.07 / $0.30 per 1M
`e2ee-gpt-oss-120b-p`	E2EE	E2EE	$0.13 / $0.65 per 1M

OpenAI GPT OSS 120B specifications

Spec	Value
Provider	OpenAI
Released	Nov 6, 2025
Privacy	Private, E2EE
Status	Stable
Open weights	Yes
License	Apache 2.0
Context window	128K tokens
Max output	16K tokens
Reasoning effort	none, low, medium, high

How to use the OpenAI GPT OSS 120B API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "openai-gpt-oss-120b" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai-gpt-oss-120b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "low"
  }'

Related models

Google Gemma 3 27B Instruct API: $0.12 / $0.20 per 1M
Mistral Small 3.2 24B Instruct API: $0.0938 / $0.25 per 1M
NVIDIA Nemotron 3 Nano 30B API: $0.075 / $0.30 per 1M
GLM 4.7 Flash Heretic API: $0.07 / $0.40 per 1M

Explore

By modality