Meta · deprecated

Llama 4 Scout 17B Instruct

Llama 4 Scout 17B Instruct is attributed to Meta in the catalog. It accepts text and image input and produces text output. Reported capabilities include tool calling.

Compare model

Report an error Model and price history

Modalities

Hosted provider token rates

$0.08 / $0.24

USD per 1M input / output tokens · Kilo Gateway

Context

10M

Released

2025-04-05

Knowledge cutoff

Aug 2024

No recent lab-operated provider rate is available. Showing the third-party host with the lowest input rate + ¼ output rate. This is one offering, not an average; other providers, modalities, tiers, and fees may differ.

Where to use it

16 observed offerings · token prices in USD per million where available

Estimate your workload cost

Amazon Bedrock

meta.llama4-scout-17b-instruct-v1:0

deprecated

Input

$0.17

Output

$0.66

Cache

—

Context

10M

Max output

Reasoning: No
Tool calling: Yes
Structured output: No
Temperature: Yes

Not a current offering

Vertex

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

current

Input

$0.25

Output

$0.70

Cache

—

Context

1.31M

Max output

Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature: Yes

Recent price

DevPass (LLM Gateway)

llama-4-scout-17b-instruct

current

Input

$0.18

Output

$0.59

Cache

—

Context

131K

Max output

Reasoning: No
Tool calling: No
Structured output: No
Temperature: Yes

Recent price

OCI Generative AI

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

current

Input

$0.72

Output

$0.72

Cache

—

Context

192K

Max output

16K

Reasoning: No
Tool calling: No
Structured output: Unknown
Temperature: Yes

Recent price

Novita AI

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

current

Input

$0.18

Output

$0.59

Cache

—

Context

131K

Max output

131K

Reasoning: No
Tool calling: No
Structured output: Unknown
Temperature: Yes

Recent price

LLM Gateway

aws-bedrock/llama-4-scout-17b-instruct

deprecated

Input

$0.17

Output

$0.66

Cache

—

Context

Max output

Reasoning: No
Tool calling: No
Structured output: No
Temperature: Yes

Not a current offering

LLM Gateway

novita/llama-4-scout-17b-instruct

current

Input

$0.18

Output

$0.59

Cache

—

Context

131K

Max output

131K

Reasoning: No
Tool calling: No
Structured output: No
Temperature: Yes

Recent price

Amazon Bedrock

us.meta.llama4-scout-17b-instruct-v1:0

deprecated

Input

$0.17

Output

$0.66

Cache

—

Context

10M

Max output

Reasoning: No
Tool calling: Yes
Structured output: No
Temperature: Yes

Not a current offering

Cloudflare Workers AI

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

current

Input

$0.27

Output

$0.85

Cache

—

Context

131K

Max output

16K

Reasoning: No
Tool calling: Yes
Structured output: No
Temperature: Yes

Recent price

Azure

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

current

Input

$0.20

Output

$0.78

Cache

—

Context

128K

Max output

Reasoning: No
Tool calling: Yes
Structured output: Unknown
Temperature: Yes

Recent price

Azure Cognitive Services

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

current

Input

$0.20

Output

$0.78

Cache

—

Context

128K

Max output

Reasoning: No
Tool calling: Yes
Structured output: Unknown
Temperature: Yes

Recent price

Kilo Gateway

meta-llama/llama-4-scout

current

Input

$0.08

Output

$0.24

Cache

—

Context

328K

Max output

16K

Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature: Yes

Recent price

NanoGPT

meta-llama/llama-4-scout

current

Input

$0.085

Output

$0.46

Cache

$0.0425

Context

328K

Max output

66K

Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature: Yes

Recent price

OpenRouter

meta-llama/llama-4-scout

current

Input

$0.10

Output

$0.30

Cache

—

Context

328K

Max output

16K

Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature: Yes

Recent price

Helicone

llama-4-scout

current

Input

$0.08

Output

$0.30

Cache

—

Context

131K

Max output

Reasoning: No
Tool calling: Yes
Structured output: Unknown
Temperature: Yes

Recent price

Deep Infra

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

current

Input

$0.10

Output

$0.30

Cache

—

Context

328K

Max output

16K

Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature: Yes

Recent price

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Provider / API ID	Status	Context	Max output	Input	Output	Cache read	Reasoning	Tools	Structured	Temperature
Amazon Bedrock meta.llama4-scout-17b-instruct-v1:0	deprecatedNot a current offering	10M	8K	$0.17	$0.66	—	No	Yes	No	Yes
Vertex meta/llama-4-scout-17b-16e-instruct-maas	currentRecent price	1.31M	8K	$0.25	$0.70	—	No	Yes	Yes	Yes
DevPass (LLM Gateway) llama-4-scout-17b-instruct	currentRecent price	131K	2K	$0.18	$0.59	—	No	No	No	Yes
OCI Generative AI meta.llama-4-scout-17b-16e-instruct	currentRecent price	192K	16K	$0.72	$0.72	—	No	No	Unknown	Yes
Novita AI meta-llama/llama-4-scout-17b-16e-instruct	currentRecent price	131K	131K	$0.18	$0.59	—	No	No	Unknown	Yes
LLM Gateway aws-bedrock/llama-4-scout-17b-instruct	deprecatedNot a current offering	8K	2K	$0.17	$0.66	—	No	No	No	Yes
LLM Gateway novita/llama-4-scout-17b-instruct	currentRecent price	131K	131K	$0.18	$0.59	—	No	No	No	Yes
Amazon Bedrock us.meta.llama4-scout-17b-instruct-v1:0	deprecatedNot a current offering	10M	8K	$0.17	$0.66	—	No	Yes	No	Yes
Cloudflare Workers AI @cf/meta/llama-4-scout-17b-16e-instruct	currentRecent price	131K	16K	$0.27	$0.85	—	No	Yes	No	Yes
Azure llama-4-scout-17b-16e-instruct	currentRecent price	128K	8K	$0.20	$0.78	—	No	Yes	Unknown	Yes
Azure Cognitive Services llama-4-scout-17b-16e-instruct	currentRecent price	128K	8K	$0.20	$0.78	—	No	Yes	Unknown	Yes
Kilo Gateway meta-llama/llama-4-scout	currentRecent price	328K	16K	$0.08	$0.24	—	No	Yes	Yes	Yes
NanoGPT meta-llama/llama-4-scout	currentRecent price	328K	66K	$0.085	$0.46	$0.0425	No	Yes	Yes	Yes
OpenRouter meta-llama/llama-4-scout	currentRecent price	328K	16K	$0.10	$0.30	—	No	Yes	Yes	Yes
Helicone llama-4-scout	currentRecent price	131K	8K	$0.08	$0.30	—	No	Yes	Unknown	Yes
Deep Infra meta-llama/Llama-4-Scout-17B-16E-Instruct	currentRecent price	328K	16K	$0.10	$0.30	—	No	Yes	Yes	Yes

Capabilities and limits

Input: text, image
Output: text
Max output: 8K
Weights: Open (source-reported)
Release: 2025-04-05
Knowledge cutoff: Aug 2024
Family: llama

Tool calling · Vision

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Model and price history

Latest recorded change: source refresh · 2026-10-22

Model changes (11)

source refresh · 2026-10-22

{
  "before": {
    "status": "current"
  },
  "after": {
    "status": "deprecated"
  }
}

source refresh · 2026-10-21

{
  "before": {
    "knowledge_cutoff_reported": null
  },
  "after": {
    "knowledge_cutoff_reported": "2024-08"
  }
}

source refresh · 2026-10-20

{
  "before": {
    "status": "current"
  },
  "after": {
    "status": "deprecated"
  }
}

source refresh · 2026-10-20

{
  "before": {
    "status": "current"
  },
  "after": {
    "status": "deprecated"
  }
}

source refresh · 2026-10-20

{
  "before": {
    "open_weights": false,
    "knowledge_cutoff_reported": null
  },
  "after": {
    "open_weights": true,
    "knowledge_cutoff_reported": "2024-08"
  }
}

price change · 2026-10-17

{
  "before": {
    "input": "0.10000000",
    "output": "0.30000000",
    "provider": "Kilo Gateway"
  },
  "after": {
    "input": 0.08,
    "output": 0.24,
    "provider": "Kilo Gateway"
  }
}