---
title: "Llama 4 Scout API Pricing (Meta): $0.11/$0.34 per Mtok"
description: "Llama 4 Scout pricing (Meta): $0.11/1M input tokens, $0.34/1M output, 10M-token context. Meta's open-weight Llama 4 Scout — a natively multimodal MoE (17B…"
url: "https://modelpricewatch.com/models/llama-4-scout/"
source: "Model Price Watch — modelpricewatch.com"
license: "Free to cite with attribution and a link back."
note: "Prices change often. For live values prefer https://modelpricewatch.com/api/v1/models.json"
---

# Llama 4 Scout

by [Meta](https://modelpricewatch.com/providers/meta/) · 17B (16 experts) parameters

Retired open weights open weights cheap tier

[Email me when Llama 4 Scout gets cheaper](https://modelpricewatch.com/alerts/#model=meta-llama-4-scout)

**Retired on Jul 17, 2026.** No longer served on the endpoint we price — the figures below are kept for historical reference only.

**Availability:** Meta does not sell this model per token; its developer rate card (dev.meta.ai/docs/pricing-rate-limits) prices only Muse models. The price on this row was Groq's, and Groq shut meta-llama/llama-4-scout-17b-16e-instruct down for self-serve accounts on 2026-07-17 (console.groq.com/docs/deprecations; enterprise contracts are excepted). The same price on Groq's own row, groq-llama-4-scout, has been Retired since then. The rate shown is the last public per-token price Groq charged, and you can no longer buy it. Llama 4 Scout is still sold per token by other hosts; see deepinfra-llama-4-scout.

## Today's price · per 1M tokens

- **Input:** $0.110 (per 1M tokens)
- **Output:** $0.340 (per 1M tokens)
- **Blended:** $0.168 (blended $/1M — 3:1 weighted input:output)

Source: [official Meta pricing](https://console.groq.com/docs/models) · read Oct 19, 2026 MODELPRICEWATCH.COM · 2026-11-06

## Price receipt

Historical price.This model is retired — withdrawn on Jul 17, 2026 — so the provider no longer sells it and its page can no longer confirm this number: a price for a model no longer on sale is unconfirmable by definition, not missing. The figures above are the last prices we recorded for this model, kept as a historical record rather than a live quote.

**Llama 4 Scout** is still sold by [DeepInfra](https://modelpricewatch.com/providers/deepinfra/) at $0.150 blended per 1M tokens ([host details →](https://modelpricewatch.com/models/deepinfra-llama-4-scout/))

## Overview

Meta's open-weight Llama 4 Scout — a natively multimodal MoE (17B active / 109B total, 16 experts) with an industry-leading 10M-token context, the longest of any open-weight model. Handles text, images, and video; fits on a single H100 with Int4. $0.11/$0.34 per 1M tokens.

Run it yourself

### Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

[

RunPod →

Rent GPUs by the second and serve any open-weight model yourself.

](https://runpod.io?ref=jxlnkmk6)[

Novita AI →

Serverless open-model inference billed per token — no GPU ops.

](https://novita.ai/?ref=zmi5ytl&utm_source=affiliate)[

Vast.ai →

GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

](https://cloud.vast.ai/?ref_id=599146)

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

## Capabilities

Input 2/4

Text: yes; Image: yes; Audio: no; Video: no

Output

Text: yes

Features 3/9

Prompt caching: no; Reasoning: no; Coding: no; Fast inference: no; Long context: yes; Open weights: yes; Multimodal: yes; Web search: no; Realtime: no

## Benchmark performance

accuracy % · higher is better

- **Avg benchmark score:** 46.8%
- **Perf per $/Mtok:** 279.4

GPQA Diamond

57.2%

SWE-Bench Verified

28%

LiveCodeBench

32.8%

Humanity's Last Exam

12%

ARC-AGI 2

15%

AIME 2025

45%

MMMLU

75%

BFCL

58%

HumanEval

80%

MATH 500

65%

Independent composite scores

-   **AA Intelligence Index:** 6.5 (Artificial Analysis composite across reasoning, knowledge and coding evals)
-   **AA-Omniscience Index:** \-52.1 (−100–100)
-   **GDPval-AA v2:** \-155.8 ELO (Real-world work tasks, human baseline = 1000)

How it stacks up

-   Ranks **#81** of 100 benchmarked models by **average score**
-   Ranks **#160** of 194 comparably-measured models by **percentile score**, across 13 independent measurements
-   Ranks **#26** of 194 comparably-tested models by **normalized performance per dollar**
-   Strongest at **HumanEval** — 80%, **#24** of 47

**2600** tokens/sec output **0.33s** latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Nov 3, 2026 · [See full rankings →](https://modelpricewatch.com/rankings/)

## Specifications

Provider

[Meta](https://modelpricewatch.com/providers/meta/)

Context window

10M tokens

Modality

text, image

Parameters

17B (16 experts)

Open source

Yes — open weights available

Released

Apr 6, 2025

Status

Retired ended Jul 17, 2026

Last updated

Oct 19, 2026

Tags

multimodalopen-weightsmoeretired

**Availability verified:** Oct 19, 2026 — per [Meta's own deprecation notice](https://console.groq.com/docs/deprecations)

[Official pricing page](https://console.groq.com/docs/models)

## Cost calculator

copy a line

1K tokens (in)

$0.00011

1K tokens (out)

$0.00034

100K tokens (in)

$0.011

100K tokens (out)

$0.034

1M tokens (in)

$0.110

1M tokens (out)

$0.340

10M tokens (blended)

$1.68

[Full calculator →](https://modelpricewatch.com/calculator/)

## At a glance

$ per 1M tokens

Input

$0.110/M

Output

$0.340/M

Blended

$0.168/M

Context

10M

Tier

cheap

## Embed this price

A live, auto-updating badge for your README or docs:

![Llama 4 Scout live API price](/badge/model/meta-llama-4-scout.svg)

## Price history

input $/1M

Last checked **Oct 19, 2026** · every price links to the official provider pricing page

No price changes detected — this model's pricing has been stable since we began tracking it.

## Related models

same category

[Llama 3.1 8B](https://modelpricewatch.com/models/meta-llama-3-1-8b/)

Meta · $0.058/M blended

[NVIDIA Nemotron 3.5 Lightning](https://modelpricewatch.com/models/deepinfra-nvidia-nemotron-3-5-lightning/)

DeepInfra · $0.085/M blended

[Pixtral 12B](https://modelpricewatch.com/models/mistral-pixtral-12b/)

Mistral · $0.150/M blended

[Llama 4 Scout](https://modelpricewatch.com/models/deepinfra-llama-4-scout/)

DeepInfra · $0.150/M blended

[Llama 4 Maverick](https://modelpricewatch.com/models/deepinfra-llama-4-maverick/)

DeepInfra · $0.350/M blended

[Moondream 3.1 9B A2B](https://modelpricewatch.com/models/moondream-3-1-9b-a2b/)

Moondream · $0.475/M blended

## Structured data

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "Organization",
      "@id": "https://modelpricewatch.com/#org",
      "name": "Model Price Watch",
      "alternateName": [
        "ModelPriceWatch",
        "modelpricewatch",
        "Model Price Watch — The LLM Price Index"
      ],
      "url": "https://modelpricewatch.com/",
      "logo": "https://modelpricewatch.com/icon-512.png",
      "description": "Independent, automated tracker of LLM API pricing across all major providers. Every price is traced to the provider's official pricing page and re-verified on a schedule.",
      "foundingDate": "2026-06-24",
      "knowsAbout": [
        "LLM API pricing",
        "token cost per million tokens",
        "large language model cost comparison",
        "AI inference pricing",
        "prompt caching pricing"
      ],
      "publishingPrinciples": "https://modelpricewatch.com/about/#verified",
      "sameAs": [
        "https://huggingface.co/datasets/modelpricewatch/llm-token-price-history",
        "https://github.com/romanshumy/llm-prices-data",
        "https://www.npmjs.com/package/@modelpricewatch/mcp"
      ]
    },
    {
      "@type": "WebSite",
      "@id": "https://modelpricewatch.com/#website",
      "url": "https://modelpricewatch.com/",
      "name": "Model Price Watch",
      "publisher": {
        "@id": "https://modelpricewatch.com/#org"
      },
      "potentialAction": {
        "@type": "SearchAction",
        "target": {
          "@type": "EntryPoint",
          "urlTemplate": "https://modelpricewatch.com/?q={search_term_string}"
        },
        "query-input": "required name=search_term_string"
      }
    },
    {
      "@type": "Dataset",
      "@id": "https://modelpricewatch.com/#dataset",
      "name": "LLM API Pricing Dataset",
      "description": "Token pricing (input, output, and blended cost per million tokens), context windows, and price history for 306 tracked large language models across 41 providers. Every price links to the provider's official pricing page; the dataset is refreshed twice daily.",
      "url": "https://modelpricewatch.com/",
      "creator": {
        "@id": "https://modelpricewatch.com/#org"
      },
      "isAccessibleForFree": true,
      "license": "https://creativecommons.org/licenses/by/4.0/",
      "keywords": [
        "LLM API pricing",
        "token cost",
        "price per million tokens",
        "GPT pricing",
        "Claude pricing",
        "Gemini pricing",
        "LLM cost comparison"
      ],
      "variableMeasured": [
        "input price per million tokens",
        "output price per million tokens",
        "blended cost per million tokens",
        "context window"
      ],
      "temporalCoverage": "2026-06-24/",
      "dateModified": "2026-11-06T00:00:00Z",
      "distribution": [
        {
          "@type": "DataDownload",
          "encodingFormat": "application/json",
          "contentUrl": "https://modelpricewatch.com/api/v1/models.json"
        },
        {
          "@type": "DataDownload",
          "encodingFormat": "application/json",
          "contentUrl": "https://modelpricewatch.com/api/v1/price-history.json"
        }
      ]
    }
  ]
}
{
  "@context": "https://schema.org",
  "@type": "SoftwareApplication",
  "name": "Llama 4 Scout",
  "applicationCategory": "AIModel",
  "operatingSystem": "Cloud",
  "image": "https://modelpricewatch.com/og-default.png",
  "offers": {
    "@type": "Offer",
    "price": "0.11",
    "priceCurrency": "USD",
    "description": "Per million input tokens",
    "priceValidUntil": "2026-12-07",
    "availability": "https://schema.org/Discontinued"
  },
  "description": "Meta's open-weight Llama 4 Scout — a natively multimodal MoE (17B active / 109B total, 16 experts) with an industry-leading 10M-token context, the longest of any open-weight model. Handles text, images, and video; fits on a single H100 with Int4. $0.11/$0.34 per 1M tokens.",
  "manufacturer": "Meta"
}
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    {
      "@type": "ListItem",
      "position": 1,
      "name": "Pricing",
      "item": "https://modelpricewatch.com/"
    },
    {
      "@type": "ListItem",
      "position": 2,
      "name": "Meta",
      "item": "https://modelpricewatch.com/providers/meta/"
    },
    {
      "@type": "ListItem",
      "position": 3,
      "name": "Llama 4 Scout"
    }
  ]
}
```
