GPT-6 Luna Pro vs Mistral Small 3
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mistral Small 3 is 3.5× cheaper than GPT-6 Luna Pro on a typical 3:1 input/output mix. GPT-6 Luna Pro has the larger context window (1.1M vs 33K).
| GPT-6 Luna Pro | Mistral Small 3 | |
|---|---|---|
| Input price / 1M | $0.10 | $0.05 |
| Output price / 1M | $0.50 | $0.08 |
| Blended price (3:1) | $0.20 | $0.0575 |
| Cached input / 1M | $0.01 | — |
| Context window | 1.1M | 33K |
| Max output | 128K | 16K |
| Intelligence index | — | — |
| Coding index | — | — |
| Providers | 6 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | No |
| Reasoning | Yes | No |
| Tool calling | Yes | No |
| Released | 2026-09-22 | 2025-01-30 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, GPT-6 Luna Pro or Mistral Small 3?
Mistral Small 3 is 3.5× cheaper than GPT-6 Luna Pro on a typical 3:1 input/output mix.
GPT-6 Luna Pro vs Mistral Small 3: which has a bigger context window?
GPT-6 Luna Pro: 1,050,000 tokens. Mistral Small 3: 32,768 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: GPT-6 Luna Pro ≈ $450.00, Mistral Small 3 ≈ $140.00.
More comparisons
GPT-6 Luna Pro vs GLM 5.3 PrimeGPT-6 Luna Pro vs Qwen3.8 Max PrimeGPT-6 Luna Pro vs Command A+GPT-6 Luna Pro vs GPT-6 LunaGPT-6 Luna Pro vs GPT-6 Sol ProGPT-6 Luna Pro vs GPT-6 SolGPT-6 Luna Pro vs Claude Opus 5.5GPT-6 Luna Pro vs MiMo-V2.6-Pro-UltraSpeedGPT-6 Luna Pro vs MiMo-V2.6-FlashGPT-6 Luna Pro vs Grok 4.7GPT-6 Luna Pro vs Qwen3.8 Omni FlashGPT-6 Luna Pro vs GLM 5.3 FlashXGPT-6 Luna Pro vs DeepSeek V4.1 FlashGPT-6 Luna Pro vs GPT-6 AstraGPT-6 Luna Pro vs GPT-6 Astra ProGPT-6 Luna Pro vs Qwen3.8 Max (0902)Mistral Small 3 vs GLM 5.3 PrimeMistral Small 3 vs Qwen3.8 Max PrimeMistral Small 3 vs Command A+Mistral Small 3 vs GPT-6 LunaMistral Small 3 vs GPT-6 Sol ProMistral Small 3 vs GPT-6 SolMistral Small 3 vs Claude Opus 5.5Mistral Small 3 vs MiMo-V2.6-Pro-UltraSpeed