Appndo
All models

Llama 4 Scout 17B 16e Instruct

MetaOpen weights10.49M contextVisionTool calling

LMArena score 1279 · #272 overall · #270 in coding (2026-10-13)

Lowest price, from Lambda

Per million tokens

Input
$0.05
Output
$0.10
Cached input
—
Batch input / output
—
  • Up to 8K 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 Lambda: $0.70 a month.

Where to buy it (8)

Sorted by your monthly estimate. Prices per million tokens.

  • LambdaCheapest

    Input / output
    $0.05 / $0.10
    Context
    16K
    Per month
    $0.70

    lambda_ai/llama-4-scout-17b-16e-instruct

  • Nscale

    Input / output
    $0.09 / $0.29
    Context
    —
    Per month
    $1.48

    nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct

  • DeepInfra

    Input / output
    $0.10 / $0.30
    Context
    328K
    Per month
    $1.60

    deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct

  • Novita AI

    Input / output
    $0.18 / $0.59
    Context
    131K
    Per month
    $2.98

    novita/meta-llama/llama-4-scout-17b-16e-instruct

  • Microsoft Foundry

    Input / output
    $0.20 / $0.78
    Context
    10M
    Per month
    $3.56

    azure_ai/Llama-4-Scout-17B-16E-Instruct

  • Google Vertex AI

    Input / output
    $0.25 / $0.70
    Context
    10M
    Per month
    $3.90

    vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas

  • Cloudflare Workers AI

    Input / output
    $0.27 / $0.85
    Context
    131K
    Per month
    $4.40

    cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct

  • Oracle Cloud

    Input / output
    $0.72 / $0.72
    Context
    10.49M
    Per month
    $8.64

    oci/meta.llama-4-scout-17b-16e-instruct

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

Similar models