GPT-5.1-Codex-Max vs Llama-4-Maverick-17B-128E-Instruct-FP8
Llama-4-Maverick-17B-128E-Instruct-FP8 is cheaper on output tokens, while GPT-5.1-Codex-Max offers a larger context window. Choose GPT-5.1-Codex-Max or Llama-4-Maverick-17B-128E-Instruct-FP8 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-5.1-Codex-Max | Llama-4-Maverick-17B-128E-Instruct-FP8 |
|---|---|---|
| Provider | OpenAI | Vercel AI Gateway |
| Input / 1M tokens | $1.25 | $0.24 |
| Output / 1M tokens | $10.00 | $0.97 |
| Context window | 400K | 128K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Nov 2025 | Apr 2025 |
| LiveBench score | 74.4 | — |
| GPQA Diamond score | — | 67.0 |
| FrontierMath score | — | 0.7 |
FAQ
Is GPT-5.1-Codex-Max or Llama-4-Maverick-17B-128E-Instruct-FP8 cheaper?
Llama-4-Maverick-17B-128E-Instruct-FP8 is cheaper on output tokens ($0.97 vs $10.00 per 1M).
Which has the larger context window, GPT-5.1-Codex-Max or Llama-4-Maverick-17B-128E-Instruct-FP8?
GPT-5.1-Codex-Max has the larger context window (400K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.