Model Library
MetaReleased July 23, 2024Llama 3.1 8B
Meta · Released July 23, 2024
Intelligence score
8
At a glance
- Intelligence
- 8
- Speed
- 143.7tokens/sec
- Latency
- 1.00stime to first token
- Input price
- $0.08per 1M tokens
- Output price
- $0.10per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 8billions
Summary
Comparison summary
Llama 3.1 Instruct 8B scores 8 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). Llama 3.1 Instruct 8B generates output at 143.7 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Llama 3.1 Instruct 8B costs $0.08 per 1M input tokens (very competitive, median: $0.15) and $0.10 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Llama 3.1 8B |
|---|---|
| Provider | Meta |
| Release date | July 23, 2024 |
| Intelligence score | 8 |
| Speed | 143.7 tokens/sec |
| Latency (TTFT) | 1.00s |
| Input price | $0.08 / 1M tokens |
| Output price | $0.10 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 8B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | LLAMA 3 |
| API availability | — |
| Source | Model Intelligence legacy profile: llama-3-1-instruct-8b |
Pricing
Token prices
Price per 1M tokens
Llama 3.1 8B, as listed in the catalog record
- Input$0.08
- Output$0.10
| Token type | Price per 1M |
|---|---|
| Input | $0.08 |
| Output | $0.10 |
Model Intelligence legacy profile: llama-3-1-instruct-8b
FAQ · 20
Frequently asked questions
Llama 3.1 Instruct 8B was released on July 23, 2024.
Llama 3.1 Instruct 8B was created by Meta.
Llama 3.1 Instruct 8B scores 8 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
Llama 3.1 Instruct 8B generates output at 143.7 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Llama 3.1 Instruct 8B has a time to first token (TTFT) of 1.00s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
Llama 3.1 Instruct 8B costs $0.08 per 1M input tokens (very competitive, median: $0.15) and $0.10 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.
Llama 3.1 Instruct 8B costs $0.08 per 1M input tokens and $0.10 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.08 per 1M tokens. Pricing may vary by provider.
No, Llama 3.1 Instruct 8B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Llama 3.1 Instruct 8B supports text only input.
Llama 3.1 Instruct 8B supports text only output.
No, Llama 3.1 Instruct 8B does not support image input. It can only process text.
No, Llama 3.1 Instruct 8B is not multimodal. It only supports text only input.
Llama 3.1 Instruct 8B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Llama 3.1 Instruct 8B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Llama 3.1 Instruct 8B has 8 billion parameters.
Llama 3.1 Instruct 8B is released under the LLAMA 3.1 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.
Llama 3.1 Instruct 8B achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Llama 3.1 Instruct 8B has a knowledge cutoff of December 2023. The model's training data includes information up to this date.
Yes, Llama 3.1 Instruct 8B is available via API through 14 providers.
Llama 3.1 Instruct 8B is available through 14 API providers.