Codestral 2508 vs DeepSeek V4 Flash 0731

Price, context window & benchmark comparison

M

Codestral 2508

Mistral AI
$0.30 / $0.90
Input / Output · per 1M tokens
VS
D

DeepSeek V4 Flash 0731

DeepSeek
$0.03 / $0.32
Input / Output · per 1M tokens
Compare different models
M
D
Verdict: DeepSeek V4 Flash 0731 is 4.4× cheaper than Codestral 2508 on a typical 3:1 input/output mix. DeepSeek V4 Flash 0731 has the larger context window (1.3M vs 256K).
Codestral 2508DeepSeek V4 Flash 0731
Input price / 1M$0.30$0.03
Output price / 1M$0.90$0.32
Blended price (3:1)$0.45$0.10
Cached input / 1M$0.03$0.016
Context window256K1.3M
Max output205K944K
Intelligence index34.3
Coding index69.1
Providers30
Best provider uptime (30m)100.0%
Vision inputNoNo
ReasoningNoYes
Tool callingYesYes
Released2025-08-012026-07-31
Retirement

Cost calculator

FAQ

Which is cheaper, Codestral 2508 or DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 is 4.4× cheaper than Codestral 2508 on a typical 3:1 input/output mix.

Codestral 2508 vs DeepSeek V4 Flash 0731: which has a bigger context window?

Codestral 2508: 256,000 tokens. DeepSeek V4 Flash 0731: 1,310,720 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Codestral 2508 ≈ $1,050, DeepSeek V4 Flash 0731 ≈ $220.00.

More comparisons