Mistral Nemo pricing.
prices as of · 25 providers · 28 prices
Mistral Nemo holds 128k tokens of context. Open weights, so anyone may host it, which is why the prices below differ so much.
Mistral Nemo costs $0.15 in and $0.15 out per million tokens from Mistral AI; the cheapest price we can explain is $0.08 at Nous Portal, checked 16 Sept 2026.
Mistral AI list price
$0.60/M tokens
$0.15 in · $0.15 out
read · 83% below the market median
Cheapest price we can explain
$0.08/M tokens
$0.02 in · $0.03 out · 86% under list
Nous Portalread
What it costs for your work
Mistral AI list price
$0.099a month
cheapest we can explain · Nous Portal
$0.0126a month
difference
$0.0864saved
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Run it yourself
every plan that fits Mistral Nemo →Mistral AI publishes the weights, so you can run Mistral Nemo on a server you rent by the month. It needs about 10.3 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is HOSTKEY vm.v2-medium at $16.15/mo, streaming an estimated 2.6–5.2 tok/s.
Every provider selling Mistral Nemo
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Mistral AI's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
Mistral AIThe price Mistral AI charges for the model it trained. Every row below is measured against it.
$0.15 / $0.15in / out per M
1.00×of list price
Cheaper, and we know why
15 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Nous Portal
Resells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
131k context hereNous Portal ↗$0.02 / $0.03in / out per M
0.14×of list price
OpenRouterRoutes to a host serving the open weights; precision not disclosed.
131k context hereOpenRouter ↗$0.02 / $0.03in / out per M
0.14×of list price
Kilo GatewayRoutes to a host serving the open weights; precision not disclosed.
131k context hereKilo Gateway ↗$0.02 / $0.03in / out per M
0.14×of list price
DeepInfraServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.02 / $0.03in / out per M
0.14×of list price
ParasailServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.03 / $0.03in / out per M
0.20×of list price
TrustedRouterRoutes to a host serving the open weights; precision not disclosed.
131k context hereTrustedRouter ↗$0.03 / $0.10in / out per M
0.30×of list price
Nebius Token FactoryHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.04 / $0.12in / out per M
0.40×of list price
io.net IntelligenceHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.06 / $0.10in / out per M
0.48×of list price
NovitaHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
60k context hereNovita ↗$0.04 / $0.17in / out per M
0.48×of list price
Vercel AI GatewayRoutes to a host serving the open weights; precision not disclosed.
60k context hereVercel AI Gateway ↗$0.04 / $0.17in / out per M
0.48×of list price
- Novita
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.04 / $0.17in / out per M
0.48×of list price
$0.04 / $0.17in / out per M
0.48×of list price
- io.net Intelligence
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision fp16.
fp16 precisionio.net Intelligence ↗$0.04 / $0.16in / out per M
0.49×of list price
$0.10 / $0.12in / out per M
0.70×of list price
OVHcloud AI Endpoints7% under the list price, an ordinary reseller margin.
66k context hereOVHcloud AI Endpoints ↗$0.14 / $0.14in / out per M
0.93×of list price
Same price as the maker
7 pricesThe same price the maker charges, sold by someone else.
$0.15 / $0.15in / out per M
1.00×of list price
$0.15 / $0.15in / out per M
1.00×of list price
$0.17 / $0.17in / out per M
1.13×of list price
$0.17 / $0.17in / out per M
1.15×of list price
$0.20 / $0.20in / out per M
1.33×of list price
$0.30 / $0.30in / out per M
2.00×of list price
Helicone13233% above Mistral AI's price.
$20 / $40in / out per M
166.67×of list price
Cheaper, and nobody says why
5 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
DekaLLM0.12× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.
131k context herefp8 precision$0.02 / $0.03in / out per M
0.14×of list price
- DeepInfra
0.13× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.
131k context hereDeepInfra ↗$0.02 / $0.03in / out per M
0.14×of list price
MeganovaLists closed models at 0.80× the maker's price across its catalog.
131k context hereMeganova ↗$0.02 / $0.04in / out per M
0.17×of list price
FastRouter0.13× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.
131k context hereFastRouter ↗$0.02 / $0.04in / out per M
0.17×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
33k context hereFeatherless ↗$0.87 / $0.99in / out per M
6.00×of list price
Frequently asked
- Who sells Mistral Nemo cheapest?
- Nous Portal, at $0.02 in and $0.03 out per million tokens, read on 16 Sept 2026. Resells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
- Is Mistral Nemo open weights?
- Yes. Mistral AI publishes the weights, so anyone may host Mistral Nemo, which is why 25 providers sell it and why their prices differ so much.
- How much context does Mistral Nemo hold?
- 128,000 tokens in one call, which is about 128k, and it can call your own functions.
- How does Mistral Nemo compare with the rest of the market?
- At $0.60 per million tokens, Mistral AI's price is 83% below the $3.55 median across the 337 text models we track.