# Meta: Llama 3.3 70B Instruct

> Meta's widely used open 70B instruction model. A dependable choice for chat, summarisation and existing Llama-based workflows, with tool calling, structured output and a 128k context. Text only, without a reasoning phase.

- Model ID: `meta-llama/llama-3.3-70b-instruct`
- Maker: Meta (`meta-llama`)
- Context length: 131,072 tokens
- Input: text
- Output: text
- Capabilities: tool calling and structured output
- Page: https://tokenlane.de/models/meta-llama/llama-3.3-70b-instruct

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| IONOS | DE | yes | yes |
| OVHcloud | FR | yes | yes |
| Scaleway | FR | yes | no |

## Usage

- Base URL: `https://api.tokenlane.de/v1` (OpenAI- and OpenRouter-compatible)
- Authentication: `Authorization: Bearer $TOKENLANE_API_KEY`
- Guide: https://tokenlane.de/docs/guides/text-and-chat.md?lang=en
- Machine-readable catalogue: `GET https://api.tokenlane.de/v1/models?output_modalities=all` (public, no key)
- Documentation index for agents: https://tokenlane.de/llms.txt

```bash
curl https://api.tokenlane.de/v1/chat/completions \
  -H "Authorization: Bearer $TOKENLANE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta-llama/llama-3.3-70b-instruct","messages":[{"role":"user","content":"Hello"}]}'
```

_Catalogue snapshot: 2026-11-19T13:10:34.963Z_
