Llama 3.1 8B Instruct fp8 vs GPT OSS 120B
Llama 3.1 8B Instruct fp8 is cheaper on output tokens, while GPT OSS 120B offers a larger context window. Choose Llama 3.1 8B Instruct fp8 or GPT OSS 120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Llama 3.1 8B Instruct fp8 | GPT OSS 120B |
|---|---|---|
| Provider | Cloudflare Workers AI | Cloudflare Workers AI |
| Input / 1M tokens | $0.15 | $0.35 |
| Output / 1M tokens | $0.29 | $0.75 |
| Context window | 32K | 128K |
| Parameters | — | 117B |
| Open weights | Yes | Yes |
| Released | Jul 2024 | Aug 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.