Is Codestral (latest) or GPT-3.5 Turbo Instruct cheaper?

Codestral (latest) is cheaper on output tokens ($0.90 vs $2.00 per 1M).

Which has the larger context window, Codestral (latest) or GPT-3.5 Turbo Instruct?

Codestral (latest) has the larger context window (256K tokens).

Codestral (latest) vs GPT-3.5 Turbo Instruct

Codestral (latest) is cheaper on output tokens, while Codestral (latest) offers a larger context window. Choose Codestral (latest) or GPT-3.5 Turbo Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Codestral (latest)	GPT-3.5 Turbo Instruct
Provider	Vercel AI Gateway	Vercel AI Gateway
Input / 1M tokens	$0.30	$1.50
Output / 1M tokens	$0.90	$2.00
Context window	256K	8K
Parameters	—	20B
Open weights	Yes	No
Released	May 2024	Sep 2023

Codestral (latest) details →GPT-3.5 Turbo Instruct details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.