Back
Meta: Llama 3 8B Instruct
Llama3
Input: text
Output: text
Released: Apr 18, 2024•Updated: Mar 28, 2025
Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases.
It has demonstrated strong performance compared to leading closed-source models in human evaluations.
To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.
8,192 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| DeepInfra | deepInfra | 8K | 16K | $0.03/M | $0.06/M | 126.7 t/s | 403 ms |
| NovitaAI | novitaAi | 8K | 8K | $0.04/M | $0.04/M | 69.9 t/s | 954 ms |
| Groq | groq | 8K | 8K | $0.05/M | $0.08/M | 3310.3 t/s | 439 ms |
| Mancer (private) | mancer (private) | 16K | 2K | $0.05/M | $0.25/M | 70.2 t/s | 481 ms |
| Together | together | 8K | - | $0.10/M | $0.10/M | 168.9 t/s | 534 ms |
| Cloudflare | cloudflare | 8K | - | $0.28/M | $0.83/M | 15.8 t/s | 848 ms |
Standard Pricing
Input Tokens
$0.00000003
per 1K tokens
Output Tokens
$0.00000006
per 1K tokens