Mistral Large 2.
Mistral's flagship open-weight model — 123B dense.
1× Nvidia RTX PRO 6000 S.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
What it's best at.
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 26.1 | 591 ms | 7170 ms |
Frequently asked.
How do I run Mistral Large 2?
Where can I access Mistral Large 2?
How much does it cost to run Mistral Large 2?
Is Mistral Large 2 open-source or proprietary?
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
384 GB | — | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
192 GB | — | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
96 GB | — | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Mistral Large 2 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like Mistral Large 2, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
What it's best at.
Scores normalised against benchmark ceilings (100 = perfect). Coloured by tier — coral 80+ frontier, lavender 65+ strong, sage 50+ solid, slate below.
Published scores.
| Benchmark | Score | Source |
|---|---|---|
| MATH | 73.0 | official ↗ |
| MMLU | 84.0 | official ↗ |
| HumanEval | 92.0 | official ↗ |
Independent rankings.
About Mistral Large 2.
Mistral Large 2 is Mistral AI's flagship open-weight model (123B dense parameters), released July 2024 under the Mistral Research License — free for research and non-commercial use, paid commercial license required for production. Strong on coding and multilingual tasks; competitive with Llama 3.1 405B at 1/3 the inference cost. 128K context. Available via Mistral's own API (la Plateforme), AWS Bedrock, Azure AI, and self-hosted via vLLM.