Meta-Llama-3-70B-Instruct vs Codestral 25.01
Codestral 25.01 is cheaper on output tokens, while Codestral 25.01 offers a larger context window. Choose Meta-Llama-3-70B-Instruct or Codestral 25.01 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Meta-Llama-3-70B-Instruct | Codestral 25.01 |
|---|---|---|
| Provider | Azure | GitHub Models |
| Input / 1M tokens | $2.68 | $0.00 |
| Output / 1M tokens | $3.54 | $0.00 |
| Context window | 8K | 32K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Apr 2024 | Jan 2025 |
| GPQA Diamond score | 40.6 | — |
| Aider Polyglot score | — | 11.1 |
FAQ
Is Meta-Llama-3-70B-Instruct or Codestral 25.01 cheaper?
Codestral 25.01 is cheaper on output tokens ($0.00 vs $3.54 per 1M).
Which has the larger context window, Meta-Llama-3-70B-Instruct or Codestral 25.01?
Codestral 25.01 has the larger context window (32K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.