R1 Distill Llama 70B pricing.
prices as of · 18 providers · 19 prices
DeepSeek's R1 Distill Llama 70B holds 8k tokens of context and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.
R1 Distill Llama 70B costs $0.80 in and $0.80 out per million tokens from OpenRouter; the cheapest price we can explain is $1.20 at DeepInfra, checked 16 Sept 2026.
OpenRouter list price
$3.20/M tokens
$0.80 in · $0.80 out
read · 10% below the market median
Cheapest price we can explain
$1.20/M tokens
$0.20 in · $0.60 out · 63% under list
DeepInfraread
What it costs for your work
OpenRouter list price
$0.528a month
cheapest we can explain · DeepInfra
$0.156a month
difference
$0.372saved
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 R1 Distill Llama 70B →DeepSeek publishes the weights, so you can run R1 Distill Llama 70B on a server you rent by the month. It needs about 46.5 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is netcup VPS 8000 G12 at $46.49/mo, streaming an estimated 0.6–1.1 tok/s.
Every provider selling R1 Distill Llama 70B
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 OpenRouter's price. DeepSeek trained R1 Distill Llama 70B and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
Cheaper, and we know why
7 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- DeepInfra
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
131k context hereDeepInfra ↗$0.20 / $0.60in / out per M
0.38×of list price
RequestyRoutes to a host serving the open weights; precision not disclosed.
64k context hereRequesty ↗$0.23 / $0.69in / out per M
0.43×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.
128k context hereNebius Token Factory ↗$0.25 / $0.75in / out per M
0.47×of list price
NscaleHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.38 / $0.38in / out per M
0.47×of list price
Alibaba Cloud (China)Alibaba's China-region Model Studio, which prices the Qwen models below the international list. A region, not a deal.
33k context hereAlibaba Cloud (China) ↗$0.29 / $0.86in / out per M
0.54×of list price
OVHcloud AI EndpointsHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
131k context hereOVHcloud AI Endpoints ↗$0.67 / $0.67in / out per M
0.84×of list price
Eden AIRoutes to a host serving the open weights; precision not disclosed.
131k context hereEden AI ↗$0.70 / $0.80in / out per M
0.91×of list price
Same price as the maker
8 pricesThe same price the maker charges, sold by someone else.
$0.80 / $0.80in / out per M
1.00×of list price
$0.80 / $0.80in / out per M
1.00×of list price
$0.80 / $0.80in / out per M
1.00×of list price
$0.80 / $0.80in / out per M
1.00×of list price
$0.84 / $0.84in / out per M
1.05×of list price
$0.90 / $0.90in / out per M
1.13×of list price
$0.99 / $0.99in / out per M
1.24×of list price
$2 / $2in / out per M
2.50×of list price
Cheaper, and nobody says why
4 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
Helicone0.04× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.
128k context here$0.03 / $0.13in / out per M
0.07×of list price
FastRouter0.04× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.
131k context hereFastRouter ↗$0.03 / $0.14in / out per M
0.07×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
33k context hereFeatherless ↗$0.65 / $0.75in / out per M
0.84×of list price
SambaNovaWe could not read this provider's prices reliably, so the row is listed but never ranked.
131k context hereSambaNova ↗$0.70 / $1.40in / out per M
1.09×of list price
Frequently asked
- Who sells R1 Distill Llama 70B cheapest?
- DeepInfra, at $0.20 in and $0.60 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
- Is R1 Distill Llama 70B open weights?
- Yes. DeepSeek publishes the weights, so anyone may host R1 Distill Llama 70B, which is why 18 providers sell it and why their prices differ so much.
- How much context does R1 Distill Llama 70B hold?
- 8,192 tokens in one call, which is about 8k.
- How does R1 Distill Llama 70B compare with the rest of the market?
- At $3.20 per million tokens, OpenRouter's price is 10% below the $3.55 median across the 337 text models we track.