DeepSeek-R1-Distill-Llama-8B

Offers for DeepSeek-R1-Distill-Llama-8B, one row per offer, sorted by blended price.

Rank#	Provider · viaWhat is “via”?You buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.	Input $/1MInput $/1M	Output $/1MOutput $/1M	Blended $/1MBlended $/1MWhat is the blended price?A single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.	ContextContextWhat is the context window?The maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.	ConditionsWhat is conditions?What a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.	Signals	Offer
1	Nscalevia Hugging Facevia Hugging Face	0.05	0.05	0.05	131k			Pricing See pricing at Hugging Face (opens in a new tab)
2	Featherless	0.20	0.32	0.23	33k			Offer Go to offer at Featherless (opens in a new tab)

Training terms not published

• Nscale

  $0.05

  Hugging Face

  in

  $0.05

  out

  $0.05

  Context

  131k

  unpublishedTraining terms not published

  See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

• Featherless

  $0.23

  direct

  in

  $0.20

  out

  $0.32

  Context

  33k

  unpublishedTraining terms not published

  Go to offer Go to offer at Featherless (opens in a new tab)at Featherless

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method