by Mistral AI

Mistral Nemo 12B.

text open weights laptop+ 12B params 128K ctx
Cheapest input
$0.02/M
on Mistral La Plateforme
Cheapest output
$0.03/M
on Mistral La Plateforme
Fastest
33 tok/s
on OpenRouter
Smallest GPU
1× AMD Radeon RX 5700 XT

Mistral × Nvidia collab — 12B Apache-licensed, multilingual.

Smallest GPU to run it See all quantisations →

1× AMD Radeon RX 5700 XT.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Mistral La Plateforme api direct $0.02 $0.03 Launch ↗
OpenRouter api aggregator $0.02 $0.03 Launch ↗
Performance

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 33.5 1025 ms 2957 ms
Sources

Official references.

FAQ

Frequently asked.

How do I run Mistral Nemo 12B?
Mistral Nemo 12B is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Mistral Nemo 12B?
Mistral Nemo 12B is available via Mistral La Plateforme, OpenRouter, Ollama. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Mistral Nemo 12B?
Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.
Is Mistral Nemo 12B open-source or proprietary?
Mistral Nemo 12B is open-weight under the Apache-2.0 license. You can download and self-host it.