Codestral 2508 vs Llama 4 Scout
Price, context window & benchmark comparison
VS
Compare different models
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 2508 | Llama 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 window | 256K | 1.3M |
| Max output | 205K | 16K |
| Intelligence index | — | — |
| Coding index | — | 8.2 |
| Providers | — | 4 |
| Best provider uptime (30m) | — | 100.0% |
| Vision input | No | Yes |
| Reasoning | No | No |
| Tool calling | Yes | Yes |
| Released | 2025-08-01 | 2025-04-05 |
| 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
Codestral 2508 vs Gemini 4 CarbonCodestral 2508 vs Claude Fable 5.2Codestral 2508 vs Gemini Omni 1.2 FlashCodestral 2508 vs Gemini Omni 1.1 FlashCodestral 2508 vs Hy4Codestral 2508 vs GLM 5.3 FlashX LegalCodestral 2508 vs GPT-6.1 TerraCodestral 2508 vs GPT-6.1 Terra ProCodestral 2508 vs Kimi K3.1 ProCodestral 2508 vs MiniMax M3.1 FlashCodestral 2508 vs DeepSeek V4.1 Flash 1017Codestral 2508 vs Nemotron 3.5 Super VLCodestral 2508 vs Gemini 4 ArgonCodestral 2508 vs Claude Haiku 5.5Codestral 2508 vs Nano Banana 2.1Codestral 2508 vs Mistral Large 4Llama 4 Scout vs Gemini 4 CarbonLlama 4 Scout vs Claude Fable 5.2Llama 4 Scout vs Gemini Omni 1.2 FlashLlama 4 Scout vs Gemini Omni 1.1 FlashLlama 4 Scout vs Hy4Llama 4 Scout vs GLM 5.3 FlashX LegalLlama 4 Scout vs GPT-6.1 TerraLlama 4 Scout vs GPT-6.1 Terra Pro