Llama-4-Maverick-17B-128E-Instruct-FP8 vs GPT-5.2-Codex
Llama-4-Maverick-17B-128E-Instruct-FP8 is cheaper on output tokens, while GPT-5.2-Codex offers a larger context window. Choose Llama-4-Maverick-17B-128E-Instruct-FP8 or GPT-5.2-Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Llama-4-Maverick-17B-128E-Instruct-FP8 | GPT-5.2-Codex |
|---|---|---|
| Provider | Vercel AI Gateway | Vercel AI Gateway |
| Input / 1M tokens | $0.00 | $1.75 |
| Output / 1M tokens | $0.00 | $14.00 |
| Context window | 128K | 400K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Apr 2025 | Dec 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.