All models

DeepSeek V4 Pro 0813

DeepSeekOpen weights1.05M contextReasoningTool calling

Lowest price, from Sail

Pricing page

Per million tokens

Input
$0.92
Output
$2.77
Cached input
$0.04
Batch input / output
—
  • Up to 1.05M 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 Sail: $14.74 a month.

Where to buy it (8)

Sorted by your monthly estimate. Prices per million tokens.

  • SailCheapest

    Input / output
    $0.92 / $2.77
    Context
    1.05M
    Per month
    $14.74

    sail/deepseek-ai/DeepSeek-V4-Pro-0813

  • DeepInfra

    Input / output
    $1.30 / $2.60
    Context
    1.05M
    Per month
    $18.20

    deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813

  • W&B Inference

    Input / output
    $1.31 / $3.96
    Context
    1.05M
    Per month
    $21.02

    wandb/deepseek-ai/DeepSeek-V4-Pro-0813

  • Baseten

    Input / output
    $1.32 / $3.96
    Context
    1.05M
    Per month
    $21.12

    baseten/deepseek-ai/DeepSeek-V4-Pro-0813

  • Nebius

    Input / output
    $1.32 / $3.96
    Context
    979K
    Per month
    $21.12

    nebius/deepseek-ai/DeepSeek-V4-Pro-0813

  • Novita AI

    Input / output
    $1.32 / $3.96
    Context
    1.05M
    Per month
    $21.12

    novita/deepseek/deepseek-v4-pro-0813

  • Tencent Cloud

    Input / output
    $1.32 / $3.96
    Context
    1M
    Per month
    $21.12

    tencent/deepseek-v4-pro-0813

  • Together AI

    Input / output
    $1.32 / $3.96
    Context
    1.05M
    Per month
    $21.12

    together_ai/deepseek-ai/DeepSeek-V4-Pro-0813

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

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.