mistralai Open weights

Mistral Nemo pricing & benchmarks

Released Jul 19, 2024 · served by 3 providers

Input / 1M tokens$0.019
Output / 1M tokens$0.030
Context window131K
Cached input
1M in + 300K out$0.03

What Mistral Nemo is

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,...

Providers and prices for Mistral Nemo

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
DeepInfracheapest $0.019 $0.030 131K fp8 99.7%
Mistral $0.150 $0.150 131K 99.9%
Novita $0.040 $0.170 60K fp8 77.2%

FAQ

How much does the Mistral Nemo API cost?

$0.019 per 1M input tokens and $0.030 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.03.

Is Mistral Nemo free?

No. It is a paid model starting at $0.019 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Mistral Nemo?

DeepInfra at $0.019 input / $0.030 output per 1M tokens (fp8 quantization).

Can I self-host Mistral Nemo?

Yes — weights are published as mistralai/Mistral-Nemo-Instruct-2407 on Hugging Face, so you can run it on your own hardware.