> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# OpenAI GPT OSS 120B E2EE API

> OpenAI GPT OSS 120B E2EE API on Venice: 128K context, $0.13 input and $0.65 output per 1M tokens. End-to-end encrypted. Supports reasoning.



## OpenAI GPT OSS 120B E2EE API

OpenAI GPT OSS 120B E2EE is a large language model by OpenAI, available on the Venice API as `e2ee-gpt-oss-120b-p`. This model supports end-to-end encryption (E2EE) and runs in a Trusted Execution Environment (TEE). Your prompt is encrypted on your client and decrypted on the GPU within the TEE. The response is then encrypted and sent back to your client for decryption. Venice's system prompt and web search are disabled to preserve end-to-end encryption. Attestation evidence is available for independent verification. It is also available without end-to-end encryption, as [OpenAI GPT OSS 120B](https://docs.venice.ai/models/openai-gpt-oss-120b.md).

GPT OSS 120B running in a Trusted Execution Environment (TEE). OpenAI's open-weight 117B-parameter MoE model with configurable reasoning depth and native tool use, with hardware attestation evidence available for independent verification.

### OpenAI GPT OSS 120B E2EE API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `e2ee-gpt-oss-120b-p` | E2EE | E2EE | $0.13 / $0.65 per 1M |

### OpenAI GPT OSS 120B E2EE specifications

| Spec | Value |
| - | - |
| Provider | OpenAI |
| Released | Mar 18, 2026 |
| Privacy | E2EE |
| Status | Stable |
| Open weights | [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) |
| License | Apache 2.0 |
| Context window | 128K tokens |
| Max output | 32K tokens |
| Reasoning effort | low, medium, high |

### How to use the OpenAI GPT OSS 120B E2EE API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "e2ee-gpt-oss-120b-p"` and your API key.

This sample sends the prompt as plaintext, so the request runs TEE-only. For end-to-end encryption, send encrypted messages with the E2EE headers, as the [TEE and E2EE guide](https://docs.venice.ai/guides/features/tee-e2ee-models.md#e2ee-models) shows.

```bash theme={"system"}
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "e2ee-gpt-oss-120b-p",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "low"
  }'
```

### Related models

* [Gemma 4 Uncensored API](https://docs.venice.ai/models/gemma-4-uncensored.md): $0.1625 / $0.50 per 1M
* [GLM 5.3 Flash E2EE API](https://docs.venice.ai/models/glm-5-3-flash-e2ee.md): $0.16 / $0.54 per 1M
* [DeepSeek V4 Flash 0423 E2EE API](https://docs.venice.ai/models/deepseek-v4-flash-0423-e2ee.md): $0.182 / $0.373 per 1M
* [Google Gemma 4 26B A4B Instruct API](https://docs.venice.ai/models/google-gemma-4-26b-a4b-instruct.md): $0.13 / $0.40 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.