AI model · Meta Llama
Meta: Llama 3.2 3B Instruct available
meta-llama/llama-3.2-3b-instruct
Meta: Llama 3.2 3B Instruct costs US$ 0.05 per million input tokens and US$ 0.33 per million output tokens (OpenRouter reference price, verified 2026-11-13).
| Input price (per 1M tokens) | US$ 0.05 |
|---|---|
| Output price (per 1M tokens) | US$ 0.33 |
| Typical request (2,000 tokens in, 500 out) | US$ 0.000265 |
| Context window | 131,072 |
| Max output tokens | 117,964 |
| Announced retirement date | none |
| Knowledge cutoff | 2023-12-31 |
| Last verified | 2026-11-13 13:05:51 UTC |
Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.
Frequently asked questions
How much does Meta: Llama 3.2 3B Instruct cost?
Meta: Llama 3.2 3B Instruct costs US$ 0.05 per million input tokens and US$ 0.33 per million output tokens (OpenRouter reference price, verified 2026-11-13).
What is the context window of Meta: Llama 3.2 3B Instruct?
Meta: Llama 3.2 3B Instruct accepts up to 131,072 tokens of context.
Is Meta: Llama 3.2 3B Instruct being retired?
No retirement date has been announced for Meta: Llama 3.2 3B Instruct (checked 2026-11-13).
Other Meta Llama models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| meta-llama/llama-guard-4-12b | US$ 0.18 | US$ 0.18 | 163,840 |
| meta-llama/llama-4-maverick | US$ 0.35 | US$ 1.00 | 524,288 |
| meta-llama/llama-4-scout | US$ 0.1 | US$ 0.3 | 1,310,720 |
| meta-llama/llama-3.3-70b-instruct | US$ 0.71 | US$ 0.71 | 131,072 |
| meta-llama/llama-3.2-1b-instruct retiring 2026-11-20 | US$ 0.027 | US$ 0.201 | 60,000 |
| meta-llama/llama-3.1-70b-instruct | US$ 0.72 | US$ 0.72 | 131,072 |
| meta-llama/llama-3.1-8b-instruct | US$ 0.02 | US$ 0.04 | 131,072 |
Give your AI agent these facts
Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.
claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp
Add to CursorAdd to VS Code★ Star on GitHub
Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests
For agents
GET https://vigia.coredls.cloud/v1/models/meta-llama/llama-3.2-3b-instruct