Codestral 2508 vs Gemini 4 Carbon

Price, context window & benchmark comparison

Mistral AI

Codestral 2508

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

Gemini 4 Carbon

Google
$2.00 / $10.00
Input / Output · per 1M tokens
Compare different models
Mistral AI
Google
Verdict: Codestral 2508 is 8.9× cheaper than Gemini 4 Carbon on a typical 3:1 input/output mix. Gemini 4 Carbon has the larger context window (1M vs 256K).
Codestral 2508Gemini 4 Carbon
Input price / 1M$0.30$2.00
Output price / 1M$0.90$10.00
Blended price (3:1)$0.45$4.00
Cached input / 1M$0.03$0.10
Context window256K1M
Max output205K944K
Intelligence index—60
Coding index——
Providers—7
Best provider uptime (30m)—100.0%
Vision inputNoYes
ReasoningNoYes
Tool callingYesYes
Released2025-08-012026-11-10
Retirement——

Cost calculator

FAQ

Which is cheaper, Codestral 2508 or Gemini 4 Carbon?

Codestral 2508 is 8.9× cheaper than Gemini 4 Carbon on a typical 3:1 input/output mix.

Codestral 2508 vs Gemini 4 Carbon: which has a bigger context window?

Codestral 2508: 256,000 tokens. Gemini 4 Carbon: 1,048,576 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Codestral 2508 ≈ $1,050, Gemini 4 Carbon ≈ $9,000.

More comparisons