Codestral 2508 vs GPT-6 Luna
Price, context window & benchmark comparison
VS
Compare different models
Verdict: GPT-6 Luna is 2.2× cheaper than Codestral 2508 on a typical 3:1 input/output mix. GPT-6 Luna has the larger context window (1.1M vs 256K).
| Codestral 2508 | GPT-6 Luna | |
|---|---|---|
| Input price / 1M | $0.30 | $0.10 |
| Output price / 1M | $0.90 | $0.50 |
| Blended price (3:1) | $0.45 | $0.20 |
| Cached input / 1M | $0.03 | $0.01 |
| Context window | 256K | 1.1M |
| Max output | 205K | 128K |
| Intelligence index | — | 37.3 |
| Coding index | — | — |
| Providers | — | 7 |
| Best provider uptime (30m) | — | 100.0% |
| Vision input | No | Yes |
| Reasoning | No | Yes |
| Tool calling | Yes | Yes |
| Released | 2025-08-01 | 2026-09-22 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Codestral 2508 or GPT-6 Luna?
GPT-6 Luna is 2.2× cheaper than Codestral 2508 on a typical 3:1 input/output mix.
Codestral 2508 vs GPT-6 Luna: which has a bigger context window?
Codestral 2508: 256,000 tokens. GPT-6 Luna: 1,050,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Codestral 2508 ≈ $1,050, GPT-6 Luna ≈ $450.00.
More comparisons
Codestral 2508 vs GLM 5.3 PrimeCodestral 2508 vs Qwen3.8 Max PrimeCodestral 2508 vs Command A+Codestral 2508 vs GPT-6 Luna ProCodestral 2508 vs GPT-6 Sol ProCodestral 2508 vs GPT-6 SolCodestral 2508 vs Claude Opus 5.5Codestral 2508 vs MiMo-V2.6-Pro-UltraSpeedCodestral 2508 vs MiMo-V2.6-FlashCodestral 2508 vs Grok 4.7Codestral 2508 vs Qwen3.8 Omni FlashCodestral 2508 vs GLM 5.3 FlashXCodestral 2508 vs DeepSeek V4.1 FlashCodestral 2508 vs GPT-6 AstraCodestral 2508 vs GPT-6 Astra ProCodestral 2508 vs Qwen3.8 Max (0902)GPT-6 Luna vs GLM 5.3 PrimeGPT-6 Luna vs Qwen3.8 Max PrimeGPT-6 Luna vs Command A+GPT-6 Luna vs GPT-6 Luna ProGPT-6 Luna vs GPT-6 Sol ProGPT-6 Luna vs GPT-6 SolGPT-6 Luna vs Claude Opus 5.5GPT-6 Luna vs MiMo-V2.6-Pro-UltraSpeed