# Llama 3.2 3B Instruct

> Meta's compact Llama 3.2 3B instruction-tuned model optimized for edge devices and low-latency applications.

**ID**: `meta/llama-3.2-3b-instruct`  
**Creator**: meta  
**Category**: text  
**Context**: 131K tokens  
**Status**: Disabled (since 2026-08-19) — no longer routable or listed; kept for history/usage reference.  
**Reason**: The platform Workers AI host no longer serves this catalog id (model_unavailable). Remaining routes require a user-owned key, so the model is unlisted rather than advertised as a live hosted chat model.  
**Input**: $0.05/M  
**Output**: $0.33/M  
**Released**: 2024-09-25  
**Web page**: https://anyrouter.dev/model/meta/llama-3.2-3b-instruct

**Input modalities**: text  
**Output modalities**: text  

**Tokenizer**: Llama

**Capabilities**: chat, streaming, function-calling, coding

**Aliases**: `meta-llama/llama-3.2-3b-instruct`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/llama-3.2-3b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| blackbox-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| Cloudflare AI Workers | $0.05/M | $0.34/M |

## Benchmarks

- **GPQA Diamond**: 0.3
- **HLE**: 0.1

## Source

- Upstream docs: https://developers.cloudflare.com/workers-ai/models/llama-3.2-3b-instruct/