Llama 3.1 405B Instruct
Specifications
- Input
- Output
- Context window
- 128K tokens
- Released
- Jul 2024
Performance
- Speed
- 9 t/s
- TTFT
- 1.1s
- Latency
- 253 ms
- Intelligence
- —
Pricing
- Input
- €1.75 per 1M tokens
- Output
- €1.75 per 1M tokens
About this model
Meta's flagship 405B parameter model representing the pinnacle of open-source AI. Exceptional reasoning and comprehensive knowledge for demanding applications.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- No
Knowledge horizon
Knowledge cutoff Dec 2023
Released Jul 2024
Today
Training to release 7 mo Since release 23 mo
See also
Add Model to Comparison
Search for a model to add