Mistral Nemo

Mistraltext → textHugging Face OpenRouter

The cheapest provider for Mistral Nemo is DekaLLM at $0.021 per 1M tokens (blended), charging $0.018 per 1M input and $0.03 per 1M output tokens. 6 providers serve it; the most expensive charges 7.1× as much. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

Best price

$0.021

at DekaLLM

Input / output

$0.018 / $0.03

per 1M tokens

Providers

7.1× spread

7 days

—

best price

30 days

—

best price

Context

128K

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for Mistral: Mistral Nemo, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
DekaLLMCheapest fp8	$0.018	$0.03	$0.021	best	128K	99.8%	Oct 3
DeepInfra fp8	$0.019	$0.03	$0.0218	+4%	128K	100%	Oct 3
Parasail fp8	$0.03	$0.03	$0.03	+43%	128K	99.9%	Oct 3
Io Net fp16·−19% discount	$0.0356	$0.13	$0.0591	+182%	125K	99.8%	Oct 3
Novita fp8	$0.04	$0.17	$0.0725	+245%	60K	73.9%	Oct 3
Mistraleu	$0.15	$0.15	$0.15	+614%	128K	97.6%	Oct 3

DekaLLMCheapest
$0.021
$0.018 in · $0.03 out
best
128K ctx99.8% uptimefp8
DeepInfra
$0.0218
$0.019 in · $0.03 out
+4%
128K ctx100% uptimefp8
Parasail
$0.03
$0.03 in · $0.03 out
+43%
128K ctx99.9% uptimefp8
Io Net
$0.0591
$0.0356 in · $0.13 out
+182%
125K ctx99.8% uptimefp16·−19% discount
Novita
$0.0725
$0.04 in · $0.17 out
+245%
60K ctx73.9% uptimefp8
Mistral
eu
$0.15
$0.15 in · $0.15 out
+614%
128K ctx97.6% uptime

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
Io Net	$0.0235
Mistral (eu)	$0.015

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

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,...

Released: Jul 19, 2024
First tracked: Oct 3, 2026
Canonical slug: mistralai/mistral-nemo
Weights: mistralai/Mistral-Nemo-Instruct-2407