Compare AI models

Specifications
Parameters
1.6T—
Context window
1M128k
API pricing
Input price
$0.66$0.30
Output price
$1.98$0.90
Cached input price
$0.022$0.03
Cheapest input
$0.0999Relace—
Cheapest output
$1.7424Alibaba—
$203Alibaba$105Mistral list price
These models have no shared benchmark scores.
Overview
CompanyDeepSeekMistral
Release dateAug 13 2026Jul 30 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Pro-0813 and Codestral 25.08 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 25.08 is cheaper on both input and output: $0.30 vs $0.66 per million input tokens, and $0.90 vs $1.98 per million output tokens. Figures are base-tier rates. Codestral 25.08 shipped 379 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4-Pro-0813) vs 128k (Codestral 25.08). DeepSeek-V4-Pro-0813 is open weight, while Codestral 25.08 is closed.

Direct benchmark comparisons are unavailable — DeepSeek-V4-Pro-0813 and Codestral 25.08 don't publish scores on any of the same benchmarks.