meta-llama/llama-3-8b-instruct
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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Togetherint4 | $0.140 | $0.140 | 8K | 100% |
Llama 3 8B Instruct costs $0.140 per million input tokens and $0.140 per million output tokens via OpenRouter, making it 75th cheapest of 298 paid models.
Llama 3 8B Instruct scores 6.4 on the Artificial Analysis Intelligence Index, ranking 176th of 178 benchmarked models, with a GPQA Diamond score of 30%.
Llama 3 8B Instruct generates around 63 tokens per second with 660ms time-to-first-token (p50), the 131st fastest tracked model.
Llama 3 8B Instruct supports a 8K-token context window. It accepts text input.