Appndo
All models

DeepSeek V4.1 Flash

DeepSeekOpen weights1.05M contextVisionReasoningTool calling

LMArena score 1463 · #39 overall · #18 in coding (2026-10-13)

Lowest price, from Coralbricks

Pricing page

Per million tokens

Input
$0.01
Output
$1.20
Cached input
$0
Batch input / output
—
  • Writing to the prompt cache costs $0.09 per million tokens.

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 Coralbricks: $2.50 a month.

Where to buy it (9)

Sorted by your monthly estimate. Prices per million tokens.

  • CoralbricksCheapest

    Input / output
    $0.01 / $1.20
    Context
    1.05M
    Per month
    $2.50

    coralbricks/deepseek-v4.1-flash

  • Sail

    Input / output
    $0.15 / $0.60
    Context
    1.05M
    Per month
    $2.70

    sail/deepseek-ai/DeepSeek-V4.1-Flash

  • Prism

    Input / output
    $0.17 / $0.63
    Context
    1M
    Per month
    $2.96

    prism/deepseek-v4.1-flash

  • W&B Inference

    Input / output
    $0.20 / $0.65
    Context
    1.05M
    Per month
    $3.30

    wandb/deepseek-ai/DeepSeek-V4.1-Flash

  • Microsoft Foundry

    Input / output
    $0.30 / $1.20
    Context
    1M
    Per month
    $5.40

    azure_ai/deepseek-v4.1-flash

  • Baseten

    Input / output
    $0.30 / $1.20
    Context
    1.05M
    Per month
    $5.40

    baseten/deepseek-ai/DeepSeek-V4.1-Flash

  • Nebius

    Input / output
    $0.30 / $1.20
    Context
    1.05M
    Per month
    $5.40

    nebius/deepseek-ai/DeepSeek-V4.1-Flash

  • Tencent Cloud

    Input / output
    $0.30 / $1.20
    Context
    1M
    Per month
    $5.40

    tencent/deepseek-v4.1-flash

  • Together AI

    Input / output
    $0.30 / $1.20
    Context
    1.05M
    Per month
    $5.40

    together_ai/deepseek-ai/DeepSeek-V4.1-Flash

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

Similar models