Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct
📌 Model Overview
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
Llama-3.3-70B-Instruct is a Open Weights model developed by Meta, released on 2024-12-06. It is designed primarily for Chat Reasoning workloads. Featuring a 128K tokens context window and 70B parameter count, it offers robust performance for enterprise integration, developers, and researchers.
✨ Key Features & Capabilities
| Feature | Description |
|---|---|
| Context Window | 128K tokens capacity for extended prompts and multi-turn workflows |
| Primary Task | Optimized for Chat Reasoning |
| Deployment | self-hostable, api-only |
| Modality | text |
| Max Output | Max Output: 4K tokens |
| Tool / function calling support | Tool / function calling support |
⚙️ Technical Specifications
| Specification | Details |
|---|---|
| Developer / Lab | Meta |
| Release Date | 2024-12-06 |
| Model Type | Open Weights |
| Parameters | 70B |
| Context Window | 128K tokens |
| License | Llama-3.3 |
| Model Family | llama |
📊 Benchmarks & Performance
| Benchmark | Score | Source |
|---|---|---|
| Artificial Analysis Coding Index | 10.7 (index) | Independent Eval |
| SciCode | 26% | Independent Eval |
| Terminal-Bench Hard | 3% | Independent Eval |
💰 Pricing
| Tier / Unit | Rate (USD) |
|---|---|
| 1M input tokens | $0 |
| 1M output tokens | $0 |
🔗 Resources & Links
| Resource | Link |
|---|---|
| Hugging Face | https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct |
📜 License & Usage
This model is governed by the Llama-3.3 license. Please check official developer guidelines before commercial deployment.
Key Features
Max Output: 4K tokens
Tool / function calling support
You might also want to compare
Verified Sources
Tags
Model Specs
Parameters
70B
Context Window
128K tokens
License
Llama-3.3
Deployment
Pricing
- 1M input tokens$0
- 1M output tokens$0
as of 2026-07-26
Resources & Links
Lineage
Curator Notes
Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.
Compare Specs
Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.
Compare Model