Model Library
MetaReleased April 18, 2024Llama 3 70B
Meta · Released April 18, 2024
Intelligence score
3
At a glance
- Intelligence
- 3
- Speed
- —
- Latency
- —
- Input price
- $0.65per 1M tokens
- Output price
- $2.75per 1M tokens
- Context window
- 3tokens
- Parameters
- 70billions
Summary
Comparison summary
Llama 3 Instruct 70B scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 7). Llama 3 Instruct 70B costs $0.65 per 1M input tokens (somewhat higher than average, median: $0.53) and $2.75 per 1M output tokens (somewhat higher than average, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Llama 3 70B |
|---|---|
| Provider | Meta |
| Release date | April 18, 2024 |
| Intelligence score | 3 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | $0.65 / 1M tokens |
| Output price | $2.75 / 1M tokens |
| Context window | 3 tokens |
| Parameters | 70B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | META LLAMA 3 COMMUNITY LICENSE AGREEMENT |
| API availability | — |
| Source | Model Intelligence legacy profile: llama-3-instruct-70b |
Pricing
Token prices
Price per 1M tokens
Llama 3 70B, as listed in the catalog record
- Input$0.65
- Output$2.75
| Token type | Price per 1M |
|---|---|
| Input | $0.65 |
| Output | $2.75 |
Model Intelligence legacy profile: llama-3-instruct-70b
FAQ · 18
Frequently asked questions
Llama 3 Instruct 70B was released on April 18, 2024.
Llama 3 Instruct 70B was created by Meta.
Llama 3 Instruct 70B scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 7).
Llama 3 Instruct 70B costs $0.65 per 1M input tokens (somewhat higher than average, median: $0.53) and $2.75 per 1M output tokens (somewhat higher than average, median: $1.05), based on the median across providers serving the model.
Llama 3 Instruct 70B costs $0.65 per 1M input tokens and $2.75 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 $0.86 per 1M tokens. Pricing may vary by provider.
No, Llama 3 Instruct 70B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Llama 3 Instruct 70B supports text only input.
Llama 3 Instruct 70B supports text only output.
No, Llama 3 Instruct 70B does not support image input. It can only process text.
No, Llama 3 Instruct 70B is not multimodal. It only supports text only input.
Llama 3 Instruct 70B has a context window of 8.2k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Llama 3 Instruct 70B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Llama 3 Instruct 70B has 70 billion parameters.
Llama 3 Instruct 70B is released under the META LLAMA 3 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.
Llama 3 Instruct 70B achieves a score of 3 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Llama 3 Instruct 70B has a knowledge cutoff of December 2023. The model's training data includes information up to this date.
Yes, Llama 3 Instruct 70B is available via API through 3 providers.
Llama 3 Instruct 70B is available through 3 API providers.