GPT-6 Luna vs Mistral Medium 3
Price, context window & benchmark comparison
VS
Compare different models
Verdict: GPT-6 Luna is 4.0× cheaper than Mistral Medium 3 on a typical 3:1 input/output mix. GPT-6 Luna has the larger context window (1.1M vs 131K).
| GPT-6 Luna | Mistral Medium 3 | |
|---|---|---|
| Input price / 1M | $0.10 | $0.40 |
| Output price / 1M | $0.50 | $2.00 |
| Blended price (3:1) | $0.20 | $0.80 |
| Cached input / 1M | $0.01 | $0.04 |
| Context window | 1.1M | 131K |
| Max output | 128K | 105K |
| Intelligence index | 37.3 | — |
| Coding index | — | — |
| Providers | 7 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | Yes |
| Reasoning | Yes | No |
| Tool calling | Yes | Yes |
| Released | 2026-09-22 | 2025-05-07 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, GPT-6 Luna or Mistral Medium 3?
GPT-6 Luna is 4.0× cheaper than Mistral Medium 3 on a typical 3:1 input/output mix.
GPT-6 Luna vs Mistral Medium 3: which has a bigger context window?
GPT-6 Luna: 1,050,000 tokens. Mistral Medium 3: 131,072 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: GPT-6 Luna ≈ $450.00, Mistral Medium 3 ≈ $1,800.
More comparisons
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-UltraSpeedGPT-6 Luna vs MiMo-V2.6-FlashGPT-6 Luna vs Grok 4.7GPT-6 Luna vs Qwen3.8 Omni FlashGPT-6 Luna vs GLM 5.3 FlashXGPT-6 Luna vs DeepSeek V4.1 FlashGPT-6 Luna vs GPT-6 AstraGPT-6 Luna vs GPT-6 Astra ProGPT-6 Luna vs Qwen3.8 Max (0902)Mistral Medium 3 vs GLM 5.3 PrimeMistral Medium 3 vs Qwen3.8 Max PrimeMistral Medium 3 vs Command A+Mistral Medium 3 vs GPT-6 Luna ProMistral Medium 3 vs GPT-6 Sol ProMistral Medium 3 vs GPT-6 SolMistral Medium 3 vs Claude Opus 5.5Mistral Medium 3 vs MiMo-V2.6-Pro-UltraSpeed