Codestral 2508 vs Llama 4 Scout

Price, context window & benchmark comparison

M

Codestral 2508

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

Llama 4 Scout

Meta Llama
$0.10 / $0.30
Input / Output · per 1M tokens
Compare different models
M
M
Verdict: Llama 4 Scout is 3.0× cheaper than Codestral 2508 on a typical 3:1 input/output mix. Llama 4 Scout has the larger context window (1.3M vs 256K).
Codestral 2508Llama 4 Scout
Input price / 1M$0.30$0.10
Output price / 1M$0.90$0.30
Blended price (3:1)$0.45$0.15
Cached input / 1M$0.03
Context window256K1.3M
Max output205K16K
Intelligence index
Coding index8.2
Providers3
Best provider uptime (30m)99.9%
Vision inputNoYes
ReasoningNoNo
Tool callingYesYes
Released2025-08-012025-04-05
Retirement

Cost calculator

FAQ

Which is cheaper, Codestral 2508 or Llama 4 Scout?

Llama 4 Scout is 3.0× cheaper than Codestral 2508 on a typical 3:1 input/output mix.

Codestral 2508 vs Llama 4 Scout: which has a bigger context window?

Codestral 2508: 256,000 tokens. Llama 4 Scout: 1,310,720 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Codestral 2508 ≈ $1,050, Llama 4 Scout ≈ $350.00.

More comparisons