All models

DeepSeek R1 Distill Llama 70B

DeepSeekOpen weights131K contextTool callingReasoning

Lowest price, from DeepInfra

Per million tokens

Input
$0.20
Output
$0.60
Cached input
—
Batch input / output
—
  • Up to 131K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From DeepInfra: $3.20 a month.

Where to buy it (8)

Sorted by your monthly estimate. Prices per million tokens.

  • DeepInfraCheapest

    Input / output
    $0.20 / $0.60
    Context
    131K
    Per month
    $3.20

    deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

  • Nebius

    Input / output
    $0.25 / $0.75
    Context
    128K
    Per month
    $4.00

    nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

  • Nscale

    Input / output
    $0.375 / $0.375
    Context
    —
    Per month
    $4.50

    nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

  • Ovhcloud

    Input / output
    $0.67 / $0.67
    Context
    131K
    Per month
    $8.04

    ovhcloud/DeepSeek-R1-Distill-Llama-70B

  • Vercel AI Gateway

    Input / output
    $0.75 / $0.99
    Context
    131K
    Per month
    $9.48

    vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b

  • Novita AI

    Input / output
    $0.80 / $0.80
    Context
    8K
    Per month
    $9.60

    novita/deepseek/deepseek-r1-distill-llama-70b

  • Fireworks AI

    Input / output
    $0.90 / $0.90
    Context
    131K
    Per month
    $10.80

    fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b

  • Gradient Ai

    Input / output
    $0.99 / $0.99
    Context
    33K
    Per month
    $11.88

    gradient_ai/deepseek-r1-distill-llama-70b

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling, Reasoning.

Similar models

About this data

Prices come from LiteLLM's model cost map (MIT licence), checked Oct 14, 2026; confirm on the seller's pricing page before you rely on a number.