Mistral Nemo

by Mistral · mistralai/mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Input / 1M tokens
$0.029
Output / 1M tokens
$0.03
Context
131K

Specs

Input price$0.029 / 1M tokens
Output price$0.03 / 1M tokens
Context window131K tokens
Max output16.4K tokens
Readstext
Writestext
Tool callingYes
ReasoningNo
ListedJul 19, 2024

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

5 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
Io NetCheapestfp16128K102K$0.0166$0.0216$0.0108100%398 ms38 tok/sNormal
DekaLLMfp8131K105K$0.018$0.03—100%673 ms9 tok/sNormal
DeepInfrafp8131K16.4K$0.029$0.03—100%785 ms20 tok/sNormal
ParasailFastestfp8131K105K$0.03$0.03—100%330 ms100 tok/sNormal
Mistral—131K105K$0.15$0.15$0.015100%300 ms96 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.