Codestral 2508 vs DeepSeek V4.1 Flash

Price, context window & benchmark comparison

Mistral AI

Codestral 2508

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

DeepSeek V4.1 Flash

DeepSeek
$0.022 / $0.40
Input / Output · per 1M tokens
Compare different models
Mistral AI
DeepSeek
Verdict: DeepSeek V4.1 Flash is 3.9× cheaper than Codestral 2508 on a typical 3:1 input/output mix. DeepSeek V4.1 Flash has the larger context window (1M vs 256K).
Codestral 2508DeepSeek V4.1 Flash
Input price / 1M$0.30$0.022
Output price / 1M$0.90$0.40
Blended price (3:1)$0.45$0.12
Cached input / 1M$0.03$0.004
Context window256K1M
Max output205K944K
Intelligence index——
Coding index——
Providers—36
Best provider uptime (30m)—100.0%
Vision inputNoYes
ReasoningNoYes
Tool callingYesYes
Released2025-08-012026-09-10
Retirement——

Cost calculator

FAQ

Which is cheaper, Codestral 2508 or DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is 3.9× cheaper than Codestral 2508 on a typical 3:1 input/output mix.

Codestral 2508 vs DeepSeek V4.1 Flash: which has a bigger context window?

Codestral 2508: 256,000 tokens. DeepSeek V4.1 Flash: 1,048,576 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Codestral 2508 ≈ $1,050, DeepSeek V4.1 Flash ≈ $244.00.

More comparisons