# Llama 3.1 8B Instruct API prices

Llama 3.1 8B Instruct (llama) — 131k context, 131k max output.
15 metered per-token offers from 15 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Inference | $0.025 | $0.025 | — | 16k |
| Kilo Gateway | $0.02 | $0.04 | — | 131k |
| Helicone | $0.02 | $0.05 | — | 16k |
| Abacus | $0.02 | $0.05 | — | 128k |
| NovitaAI | $0.02 | $0.05 | — | 16k |
| OpenRouter | $0.05 | $0.08 | $0.025 | 131k |
| Hugging Face | $0.06 | $0.06 | — | 131k |
| NanoGPT | $0.0544 | $0.085 | $0.0272 | 131k |
| Cortecs | $0.167 | $0.167 | — | 128k |
| DigitalOcean | $0.198 | $0.198 | — | 131k |
| Pioneer | $0.2 | $0.2 | $0.2 | 128k |
| Amazon Bedrock | $0.22 | $0.22 | — | 128k |
| Amazon Bedrock (us) | $0.22 | $0.22 | — | 128k |
| Vercel AI Gateway | $0.22 | $0.22 | — | 128k |
| Neon | $0.15 | $0.45 | — | 131k |

## Summary

- Cheapest input: $0.02 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.025 per 1M tokens (Inference)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2024-07-23
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/llama-3-1-8b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json