> ## 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.

# Llama 3.3 70B API

> Llama 3.3 70B API on Venice: 128K context, $0.70 input and $2.80 output per 1M tokens. Private, with zero data retention. Supports function calling.



## Llama 3.3 70B API

Llama 3.3 70B is a large language model by Meta, available on the Venice API as `llama-3.3-70b`. This model is private and no prompt data is stored in any capacity.

Llama 3.3 70B is Meta's instruction-tuned 70-billion-parameter Llama model, which Meta reports performs close to its much larger Llama 3.1 405B on many tasks. It supports text input and output with a 128K-token context window, for chat, writing and code.

### Llama 3.3 70B API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `llama-3.3-70b` | Standard | Private | $0.70 / $2.80 per 1M |

### Llama 3.3 70B specifications

| Spec | Value |
| - | - |
| Provider | Meta |
| Released | Apr 6, 2025 |
| Privacy | Private |
| Status | Stable |
| Open weights | [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) |
| Context window | 128K tokens |
| Max output | 4K tokens |
| Served precision | FP8 |
| [GPQA Diamond](https://docs.venice.ai/models/methodology.md#benchmarks) | 50.5% ±7.0 (95% interval), run by Venice through the API on Oct 21, 2026 |

### How to use the Llama 3.3 70B API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "llama-3.3-70b"` and your API key.

```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": "llama-3.3-70b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'
```

### Related models

* [Llama 3.2 3B API](https://docs.venice.ai/models/llama-3-2-3b.md): $0.15 / $0.60 per 1M
* [Qwen 3 235B A22B Thinking 2507 API](https://docs.venice.ai/models/qwen-3-235b-a22b-thinking-2507.md): $0.45 / $3.50 per 1M
* [GLM 4.7 API](https://docs.venice.ai/models/glm-4-7.md): $0.55 / $2.65 per 1M
* [Gemini 3 Flash Preview API](https://docs.venice.ai/models/gemini-3-flash-preview.md): $0.70 / $3.75 per 1M
* [Qwen 3 Next 80b API](https://docs.venice.ai/models/qwen-3-next-80b.md): $0.35 / $1.90 per 1M


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