Engineering ready
Mistral Large 3 675B Instruct 2512 FP8 Production Package
Mistral / Mistral Large 3 675B Instruct 2512 · FP8 · Engineering status: Engineering ready
Transformation lineage
Base releaseMistral Large 3 675B Instruct 2512
Model engineeringFP8 Quantization, Runtime packaging, Evaluation and benchmarking
Delivery optionsDownload package / Host with FusionPointAI / Download + host
Transparent pricing
- Base model engineeringUSD 95,700.00
- FP8 QuantizationUSD 5,900.00
- Runtime packagingUSD 2,800.00
- Evaluation and benchmarkingUSD 3,600.00
- Download packageUSD 1,500.00
- Managed deployment setupUSD 3,200.00
- One-time engineeringUSD 112,700.00
Monthly hosting
- 7 x nvidia-h200-sxm-141gbUSD 16,415.00
- Monthly hostingUSD 16,415.00
Quantization
SourceSource
TransformationEstimated until measured during engineering
GPU topology
7 × nvidia-h200-sxm-141gb
vllm
Download or managed hosting
Artifact, config, tokenizer, checksums
GPU allocation, runtime, endpoint and monitoring