Gradient Llama 3 Models by Gradient
4 models2024Up to 1.05m ctxFrom $0.37/1M input
About
Long context windows for Llama 3
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view
Llama 3 8B Gradient 1048KCurrent
Use when the workload needs 1.05m context and 8B parameters.
2024-041.05m context8B parameters
Llama 3 70B Gradient 1048KCurrent
Use when the workload needs 1.05m context and 70B parameters.
2024-041.05m context70B parameters
Llama 3.1 8B Gradient 1048KCurrent
Use when the workload needs 1.05m context and 8B parameters.
2024-041.05m context8B parameters
Llama 3 8B Gradient 262KCurrent
Use when the workload needs 262k context and 8B parameters.
2024-04262k context8B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Llama 3 8B Gradient 1048K | Use when the workload needs 1.05m context and 8B parameters. | 2024-04 | 1.05m context8B parameters | Current |
| Llama 3 70B Gradient 1048K | Use when the workload needs 1.05m context and 70B parameters. | 2024-04 | 1.05m context70B parameters | Current |
| Llama 3.1 8B Gradient 1048K | Use when the workload needs 1.05m context and 8B parameters. | 2024-04 | 1.05m context8B parameters | Current |
| Llama 3 8B Gradient 262K | Use when the workload needs 262k context and 8B parameters. | 2024-04 | 262k context8B parameters | Current |
Release Timeline
1 release group2024-04
4 current
Llama 3 70B Gradient 1048K
Current1.05m context70B parameters
Llama 3 8B Gradient 1048K
Current1.05m context8B parameters
Llama 3 8B Gradient 262K
Current262k context8B parameters
Llama 3.1 8B Gradient 1048K
Current1.05m context8B parameters
Specifications(4 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Llama 3 8B Gradient 1048K | 2024-04 | 1.05m | 8B |
| Llama 3 70B Gradient 1048K | 2024-04 | 1.05m | 70B |
| Llama 3.1 8B Gradient 1048K | 2024-04 | 1.05m | 8B |
| Llama 3 8B Gradient 262K | 2024-04 | 262k | 8B |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Llama 3 8B Gradient 262K | Microsoft Foundry | $0.37 | $1.1 | Provisioned |
Frequently Asked Questions
- What is Gradient Llama 3 used for?
- Long context windows for Llama 3
- How does Gradient Llama 3 compare to Claude 3?
- Gradient Llama 3 by Gradient is strongest where you need its listed use cases, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. Gradient Llama 3 has 4 listed variants and reaches up to 1.05m context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which Gradient Llama 3 model should I use?
- For the lowest listed input price, start with Llama 3 8B Gradient 262K through Microsoft Foundry at $0.37/1M input tokens. For the most capable/latest local choice, evaluate Llama 3 8B Gradient 1048K with 1.05m context.