Meta Models
Explore the Meta language and embedding models available through our OpenAI Assistants API-compatible service.
Meta: Llama 3.1 8B Instruct
- Context Length:
- 131,072 tokens
- Architecture:
- text->text
- Max Output:
- 4,096 tokens
Pricing:
Meta has unveiled its latest model, Llama 3.1, offering a diverse range of sizes and configurations. Among these, the 8B instruct-tuned version stands out for its speed and efficiency. In rigorous human evaluations, this model has showcased impressive performance, rivaling leading closed-source alternatives.
For a detailed exploration of the Llama 3.1 release, visit the official blog. It's important to note that the use of this model is governed by Meta's Acceptable Use Policy.
Meta: Llama 3 8B Instruct
- Context Length:
- 8,192 tokens
- Architecture:
- text->text
- Max Output:
- 4,096 tokens
Pricing:
Meta has unveiled its latest innovation, the Llama 3 model series, offering a range of sizes and specialized versions to meet diverse needs. Among these, the 8B instruct-tuned variant stands out, meticulously optimized for delivering high-quality dialogue interactions.
In rigorous human evaluations, this model has showcased impressive performance, rivaling even the top closed-source models in the field.
For a deeper dive into the Llama 3 release and its capabilities, explore the full details here. Please note that use of this model is governed by Meta's Acceptable Use Policy, ensuring responsible and ethical deployment.
Meta: Llama 3.1 70B Instruct
- Context Length:
- 131,072 tokens
- Architecture:
- text->text
- Max Output:
- 4,096 tokens
Pricing:
Meta has unveiled its latest model series, Llama 3.1, offering a range of sizes and configurations. Among these, the 70B instruct-tuned version stands out, specifically optimized for delivering high-quality dialogue interactions.
In human evaluations, this model has shown impressive performance, rivaling leading closed-source alternatives.
For more details on the Llama 3.1 release, visit the official blog. Usage of this model is governed by Meta's Acceptable Use Policy.
Meta: Llama 3 70B Instruct
- Context Length:
- 8,192 tokens
- Architecture:
- text->text
- Max Output:
- 4,096 tokens
Pricing:
Meta has introduced its latest generation of models, Llama 3, available in a range of sizes and configurations. Among these, the 70B instruct-tuned version stands out, specifically optimized for delivering high-quality dialogue interactions.
In human evaluations, this model has shown impressive performance, rivaling even the leading closed-source models in the field.
For more details on the Llama 3 release, visit the official blog. Please note that the use of this model is governed by Meta's Acceptable Use Policy.
Meta: Llama 3.1 405B Instruct
- Context Length:
- 131,072 tokens
- Architecture:
- text->text
- Max Output:
- 4,096 tokens
Pricing:
Introducing the highly anticipated Llama3 400B class, a groundbreaking advancement in open-source large language models (LLMs) from Meta AI. With an impressive 128k context window and exceptional evaluation scores, this model sets a new standard for performance and versatility.
The Llama 3.1 series offers a range of model sizes and configurations, with the 405B instruct-tuned variant specifically optimized for high-quality dialogue applications. In rigorous evaluations, it has demonstrated competitive performance against top-tier closed-source models, including GPT-4o and Claude 3.5 Sonnet, solidifying its position as a leader in the field.
For more details on this exciting release, visit the official announcement. Please note that usage of this model is governed by Meta's Acceptable Use Policy.
Ready to build with Meta?
Start using these powerful models in your applications with our flexible pricing plans.