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	$0.07 input /$ 0.30 output per 1M tokens
`e2ee-gpt-oss-120b-p`	E2EE	End-to-end encrypted	$0.13 input /$ 0.65 output per 1M tokens

OpenAI GPT OSS 120B specifications

Spec	Value
Provider	OpenAI
Released	Nov 6, 2025
Privacy	Private, End-to-end encrypted
Open weights	Yes
License	Apache 2.0
Context window	125K 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"
  }'

OpenAI GPT OSS 120B API FAQ

How much does the OpenAI GPT OSS 120B API cost?

0.07 per 1M input tokens and

0.30 per 1M output tokens. The E2EE variant costs

0.13 input and

0.65 output. Prices are in USD and can be paid in DIEM at parity.

What is the OpenAI GPT OSS 120B model ID?

Use openai-gpt-oss-120b as the model parameter. Other variants: e2ee-gpt-oss-120b-p (E2EE).

Is the OpenAI GPT OSS 120B API private?

The Standard variant is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training. The E2EE variant is end-to-end encrypted: prompts are encrypted on your device and decrypted only inside an attested hardware enclave, so neither Venice nor the GPU provider can read them.

What is the context window of OpenAI GPT OSS 120B?

125K tokens of context, with up to 16K output tokens per response.

What does OpenAI GPT OSS 120B support?

OpenAI GPT OSS 120B supports function calling, reasoning and web search. Reasoning effort is adjustable with reasoning_effort: none, low, medium and high (default low).

Which endpoint does the OpenAI GPT OSS 120B API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Google Gemma 3 27B Instruct API: $0.12 input /$ 0.20 output per 1M tokens
Mistral Small 3.2 24B Instruct API: $0.09 input /$ 0.25 output per 1M tokens
NVIDIA Nemotron 3 Nano 30B API: $0.07 input /$ 0.30 output per 1M tokens
GLM 4.7 Flash API: $0.06 input /$ 0.40 output per 1M tokens

Explore

By modality