MiniMax-M3 pricing.
prices as of · 55 providers · 67 prices
MiniMax-M3 holds 1M tokens of context, reads images as well as text and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.
MiniMax-M3 costs $0.30 in and $1.20 out per million tokens from MiniMax; the cheapest price we can explain is $1.58 at Empirio Labs, checked 16 Sept 2026.
MiniMax list price
$2.10/M tokens
$0.30 in · $1.20 out
read · 41% below the market median
Cheapest price we can explain
$1.58/M tokens
$0.23 in · $0.90 out · 25% under list
Empirio Labsread
What it costs for your work
MiniMax list price
$0.252a month
cheapest we can explain · Empirio Labs
$0.189a month
difference
$0.063saved
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.
Every provider selling MiniMax-M3
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 MiniMax's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
MiniMaxThe price MiniMax charges for the model it trained. Every row below is measured against it.
$0.30 / $1.20in / out per M
1.00×of list price
Cheaper, and we know why
10 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Empirio Labs
Routes to a host serving the open weights; precision not disclosed.
1M context hereEmpirio Labs ↗$0.23 / $0.90in / out per M
0.75×of list price
Weights & BiasesHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
262k context here$0.23 / $0.96in / out per M
0.79×of list price
CoreWeaveServes the open weights at fp4, a lower precision than the maker's, so not quite the same product.
262k context herefp4 precision$0.23 / $0.96in / out per M
0.79×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.23 / $0.96in / out per M
0.79×of list price
VancineHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.24 / $0.96in / out per M
0.80×of list price
GMI CloudServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionGMI Cloud ↗$0.24 / $0.96in / out per M
0.80×of list price
TrustedRouterRoutes to a host serving the open weights; precision not disclosed.
524k context hereTrustedRouter ↗$0.24 / $1.01in / out per M
0.83×of list price
Lilac7% under the list price, an ordinary reseller margin.
$0.28 / $1.10in / out per M
0.92×of list price
$0.28 / $1.10in / out per M
0.92×of list price
DeepInfra7% under the list price, an ordinary reseller margin.
$0.28 / $1.10in / out per M
0.92×of list price
Same price as the maker
48 pricesThe same price the maker charges, sold by someone else.
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
OrcaRouterThe same price MiniMax charges.
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
Hugging Face Inference ProvidersThe same price MiniMax charges.
524k context hereHugging Face Inference Providers ↗$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
Jalapeno CloudThe same price MiniMax charges.
524k context here$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
ClinePassThe same price MiniMax charges.
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
OpenCode GoThe same price MiniMax charges.
1M context here$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
StreamLakeThe same price MiniMax charges.
1M context herefp8 precision$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
showing the 25 cheapest of 48 · every row in the open dataset
Cheaper, and nobody says why
3 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
262k context hereFeatherless ↗$0.55 / $2.20in / out per M
1.83×of list price
SambaNovaWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.60 / $2.40in / out per M
2.00×of list price
KenariWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.63 / $2.50in / out per M
2.09×of list price
Given away with limits
5 free tiers · never rankedThese providers give MiniMax-M3 away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
MiniMax Token Plan (minimaxi.com)
NVIDIA build
MiniMax Token Plan (minimax.io)- SCNet Token Plan
Volcengine Ark Coding Plan
Frequently asked
- Who sells MiniMax-M3 cheapest?
- Empirio Labs, at $0.23 in and $0.90 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
- Is MiniMax-M3 open weights?
- Yes. MiniMax publishes the weights, so anyone may host MiniMax-M3, which is why 55 providers sell it and why their prices differ so much.
- How much context does MiniMax-M3 hold?
- 1,048,576 tokens in one call, which is about 1M, and it can call your own functions.
- How does MiniMax-M3 compare with the rest of the market?
- At $2.10 per million tokens, MiniMax's price is 41% below the $3.55 median across the 337 text models we track.