llama
Compact open Llama model for lightweight chat, drafting, and self-hosting
| Provider | Model id | Context | Price | Status |
|---|---|---|---|---|
| Nvidia | meta/llama-3.1-8b-instruct | 16,000 | $0–$0 | — |
| Kilo Gateway | meta-llama/llama-3.1-8b-instruct | 131,072 | $0.02–$0.04 | — |
| Inference | meta/llama-3.1-8b-instruct | 16,000 | $0.025–$0.025 | — |
| OpenRouter | meta-llama/llama-3.1-8b-instruct | 131,072 | $0.05–$0.08 | — |
| NanoGPT | meta-llama/llama-3.1-8b-instruct | 131,072 | $0.0544–$0.085 | — |
| Hugging Face | meta-llama/Llama-3.1-8B-Instruct | 131,072 | $0.06–$0.06 | — |
| Cloudflare Workers AI | @cf/meta/llama-3.1-8b-instruct-fp8 | 32,000 | $0.152–$0.287 | — |
| Cortecs | llama-3.1-8b-instruct | 128,000 | $0.167–$0.167 | — |
| Merge Gateway | meta/llama-3.1-8b-instruct | 128,000 | $0.22–$0.22 | — |
| Amazon Bedrock | us.meta.llama3-1-8b-instruct-v1:0 | 128,000 | $0.22–$0.22 | — |
| Amazon Bedrock | meta.llama3-1-8b-instruct-v1:0 | 128,000 | $0.22–$0.22 | — |
| CoreWeave | meta-llama/Llama-3.1-8B-Instruct | 131,072 | $0.22–$0.22 | — |