Skip to content
Sovyron

Mistral Nemo

mistral-nemo131k context128k max outputreleased Jul 1, 2024Open weightsTool calling

As of Oct 4, 2026, the cheapest Mistral Nemo API price is $0.019 per 1M input tokens (OpenRouter) and $0.03 per 1M output tokens (OpenRouter). Mistral Nemo is offered by 8 providers in the mistral-nemo family, open weights. Mistral's own rate is $0.15 per 1M output tokens.

Cheapest input
$0.019
Cheapest output
$0.03
Official (Mistral)
$0.15
output per 1M tokens
Providers
8
offering this model
Spread
1333.3×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Mistral Nemo API prices by provider in USD per 1M tokens, updated Oct 4, 2026
OpenRouteropenCheapest$0.019Cheapest$0.03——131k—
Pioneeropen$0.02$0.03$0.02$0.02128k—
NovitaAIopen$0.04$0.17——60k—
Vercel AI Gateway$0.04$0.17——60k18d agoout +13.3%
NanoGPTopen$0.1003$0.1207$0.0502—16k—
Kilo Gatewayopen$0.15$0.15$0.015—131k9d agoout +400%
Mistralopen$0.15$0.15——128k—
Helicone$20$40——128k—

Mistral Nemo pricing FAQ

What is the cheapest Mistral Nemo API?

As of Oct 4, 2026, OpenRouter has the lowest Mistral Nemo output price at $0.03 per 1M tokens, and OpenRouter has the lowest input price at $0.019 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does Mistral Nemo cost on Mistral?

Mistral charges $0.15 per 1M input tokens and $0.15 per 1M output tokens for Mistral Nemo.

How many providers offer Mistral Nemo?

8 providers list Mistral Nemo on Sovyron; 8 of them sell it at a metered per-token price.

Is Mistral Nemo free?

No provider in the Sovyron catalog lists a free tier for Mistral Nemo.

What is the context window of Mistral Nemo?

Mistral Nemo supports a 131k-token context window and up to 128k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.

Estimated

—