Llama 3 Models by AI at Meta
Last refreshed 2026-10-17. Next refresh: weekly.
Details
Capabilities
About
Llama 3, developed by Meta AI and released in April 2024, represents a significant advancement in large language models (LLMs). Available in two configurations—8 billion and 70 billion parameters—the models offer both pretrained and instruction-tuned versions, enhancing their adaptability and effectiveness in dialogue scenarios. Llama 3 sets itself apart by being trained on over 15 trillion tokens of publicly available data, a massive expansion over its predecessor, Llama 2, and includes a substantial increase in code data. The models not only excel in performance but also incorporate robust safety features like Llama Guard 2 and Code Shield, underscoring Meta's focus on responsible AI use. Llama 3 models are accessible on platforms such as AWS, Google Cloud, and Hugging Face, with plans for future updates that will expand their capabilities to include multimodal functionalities and multilingual support.
Decision facts
- Best fit
- JSON / Tool usestructured outputscoding
- Capability starting point
- Llama 3 70B with 8K context
- Lowest tracked input
- Llama 3 8B Instruct · $0.020/1M · DeepInfra
- Closest related family
- Agents-A1
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 8K context, 8B parameters, and JSON / Tool use.
Use when the workload needs 8K context and 70B parameters.
Use when the workload needs 8K context and 8B parameters.
Use when the workload needs 8K context and 70B parameters.
Use when the workload needs 8K context and 8B parameters.
Use when the workload needs 8K context, 70B parameters, and structured outputs.
Use when the workload needs 8K context, 8B parameters, and structured outputs.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Together AI - Llama 3 8B Lite | Use when the workload needs 8K context, 8B parameters, and JSON / Tool use. | 2025-07 | 8K context8B parametersJSON / Tool use | Current |
| Llama 3 Taiwan 70B Instruct | Use when the workload needs 8K context and 70B parameters. | 2024-07 | 8K context70B parameters | Current |
| Fireworks Llama-3-8B-Instruct | Use when the workload needs 8K context and 8B parameters. | 2024-04 | 8K context8B parameters | Current |
| Llama 3 70B | Use when the workload needs 8K context and 70B parameters. | 2024-04 | 8K context70B parameters | Current |
| Llama 3 8B | Use when the workload needs 8K context and 8B parameters. | 2024-04 | 8K context8B parameters | Current |
| Together AI Llama-3-70B-Instruct | Use when the workload needs 8K context, 70B parameters, and structured outputs. | 2024-04 | 8K context70B parametersstructured outputs | Current |
| Together AI Llama-3-8B-Instruct | Use when the workload needs 8K context, 8B parameters, and structured outputs. | 2024-04 | 8K context8B parametersstructured outputs | Current |
Release Timeline
3 release groupsReplaced By
Keep for legacy integrations; evaluate Llama 3.3 70B Instruct before new work.
Keep for legacy integrations; evaluate Llama 3.1 8B Instruct before new work.
Specifications(9 models)
| Model | Released | Context | Parameters | JSON / Tool use | Structured Outputs |
|---|---|---|---|---|---|
| Together AI - Llama 3 8B Lite | 2025-07 | 8K | 8B | Yes | Yes |
| Llama 3 Taiwan 70B Instruct | 2024-07 | 8K | 70B | No | No |
| Fireworks Llama-3-8B-Instruct | 2024-04 | 8K | 8B | No | No |
| Llama 3 70B | 2024-04 | 8K | 70B | No | No |
| Llama 3 8B | 2024-04 | 8K | 8B | No | No |
| Together AI Llama-3-70B-Instruct | 2024-04 | 8K | 70B | No | Yes |
| Together AI Llama-3-8B-Instruct | 2024-04 | 8K | 8B | No | Yes |
Available From(20 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Llama 3 8B | Replicate API | $0.05 | $0.25 | Serverless |
| Together AI - Llama 3 8B Lite | Together AI | $0.1 | $0.1 | Serverless |
| Fireworks Llama-3-8B-Instruct | Fireworks AI | $0.15 | $0.15 | Serverless |
| Together AI Llama-3-8B-Instruct | Together AI | $0.2 | $0.2 | Serverless |
| Llama 3 8B | Fireworks AI | $0.2 | $0.2 | Serverless |
| Together AI Llama-3-70B-Instruct | Together AI | $0.6 | $0.75 | Serverless |
| Llama 3 70B | Replicate API | $0.65 | $2.75 | Serverless |
Popular comparisons in this family
- Llama 3 70B Instruct vs Llama 3.1 70B Instruct5K
- Llama 3 70B Instruct vs Qwen2.5-72B-Instruct461
- Llama 3 70B Instruct vs Qwen3.6-27B410
- DeepSeek V4 Flash vs Llama 3 70B Instruct407
- Llama 3 70B Instruct vs Qwen3.6-35B-A3B381
- DeepSeek V4 Pro vs Llama 3 70B Instruct226
- Llama 3 70B Instruct vs Mixtral 8x7B206
- Claude Opus 4.7 vs Llama 3 70B Instruct186
- Claude Sonnet 4.6 vs Llama 3 70B Instruct181
- DeepSeek V4 Flash vs Llama 3 8B Instruct157
Models(9)
Together AI - Llama 3 8B Lite
Llama 3 Taiwan 70B Instruct
Fireworks Llama-3-8B-Instruct
Llama 3 70B
Llama 3 8B
Together AI Llama-3-70B-Instruct
Together AI Llama-3-8B-Instruct