BroadRouter
Get started

Llama 4 Scout 17B 16E Instruct API pricing

Updated

Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Llama 4 Scout 17B 16E Instruct is DeepInfra at USD 0.10 per 1M input tokens and USD 0.30 per 1M output tokens. The median across 6 standard prices is USD 0.175 / USD 0.625. Meta sells no API of its own for it.

Meta · slug llama-4-scout · up to 1,048,576 tokens of context · 6 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2025-04-08 (7 archived price points, 0 list-price changes): LLM API price history.

Does Meta sell Llama 4 Scout 17B 16E Instruct directly?

No. Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. Checked 2026-11-14.

Llama 4 Scout 17B 16E Instruct model facts

Facts from Meta's model card for meta-llama/Llama-4-Scout-17B-16E-Instruct and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Llama 4 Scout 17B 16E Instruct: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes, with gated access. meta-llama/Llama-4-Scout-17B-16E-Instruct is public, but Hugging Face asks you to request access and accept the terms before you download (gated: manual).Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": "manual", 50 .safetensors files listed”
LicenceLlama 4 Community License Agreement (custom commercial license)Meta model card, checked 2026-11-16
Quote
“A custom commercial license, the Llama 4 Community License Agreement”
Total parameters109BMeta model card, checked 2026-11-16
Quote
“Llama 4 Scout (17Bx16E) … 17B (Activated) 109B (Total)”
Active parameters per token17BMeta model card, checked 2026-11-16
Quote
“17B (Activated) 109B (Total)”
Context length10MMeta model card, checked 2026-11-16
Quote
“Multilingual text and code | 10M”
Input and outputMultilingual text and image in; multilingual text and code outMeta model card, checked 2026-11-16
Quote
“Multilingual text and image | Multilingual text and code”
Tool callingNot found on Meta's model card when we read itchecked 2026-11-16
Release date2025-04-05Meta model card, checked 2026-11-16
Quote
“Model Release Date: April 5, 2025”
First published on Hugging Face (not necessarily the release date)2025-04-02Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2025-04-02T13:34:17.000Z"”

Llama 4 Scout 17B 16E Instruct price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.8× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Llama 4 Scout 17B 16E Instruct API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra cheapest
meta-llama/Llama-4-Scout-17B-16E-Instruct
Notes and source quote
“$0.10 in $0.30 out / 1M tokens”
USD 0.10not publishedUSD 0.30USD 0.15327,680FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2GMI Cloud
meta-llama/Llama-4-Scout-17B-16E-Instruct
Notes and source quote

No cache-read price published.

“Price (per 1M tokens) Input $0.08 Output $0.50”
USD 0.08not publishedUSD 0.50USD 0.1851,048,576BF16GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
3Novita AI
meta-llama/llama-4-scout-17b-16e-instruct
Notes and source quote
“Llama 4 Scout Instruct 128K $0.18 /Mt $0.59 /Mt”
USD 0.18not publishedUSD 0.59USD 0.2825131,072not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
4Amazon Bedrock
Notes and source quote

Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“Llama 4 Scout 17B $0.17 $0.66 $0.085 $0.33”
USD 0.17not publishedUSD 0.66USD 0.2925not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
5Google Vertex AI
llama-4-scout
Notes and source quote
“Llama 4 Scout Input $0.25 … Output $0.70”
USD 0.25not publishedUSD 0.70USD 0.3625not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
6Cloudflare Workers AI
@cf/meta/llama-4-scout-17b-16e-instruct
Notes and source quote

Cloudflare publishes this USD per-token price alongside the neuron price.

“@cf/meta/llama-4-scout-17b-16e-instruct $0.270 per M input tokens $0.850 per M output tokens”
USD 0.27not publishedUSD 0.85USD 0.415not statednot statedCloudflare Workers AI page
checked 2026-11-14
re-checked 2026-11-16
—Amazon Bedrock batch
Notes and source quote

Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“Llama 4 Scout 17B $0.17 $0.66 $0.085 $0.33”
USD 0.085not publishedUSD 0.33USD 0.1462not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—Google Vertex AI batch
llama-4-scout
Notes and source quote
“Llama 4 Scout Batch Input $0.125 … Batch Output $0.35”
USD 0.125not publishedUSD 0.35USD 0.1812not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot
meta-llama/Llama-4-Scout-17B-16E-Instruct
Notes and source quote

Flex service tier (0.8× standard).

“Flex (0.8×) $0.08 $0.24”
USD 0.08not publishedUSD 0.24USD 0.12327,680FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority
meta-llama/Llama-4-Scout-17B-16E-Instruct
Notes and source quote

Priority service tier (1.5× standard).

“Priority (1.5×) $0.15 $0.45”
USD 0.15not publishedUSD 0.45USD 0.225327,680FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Llama 4 Scout 17B 16E Instruct cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Llama 4 Scout 17B 16E Instruct, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfraUSD 14.40USD 28.50USD 207.00
GMI CloudUSD 16.20USD 26.70USD 189.00
Novita AIUSD 26.82USD 52.05USD 377.10
Amazon BedrockUSD 27.18USD 50.70USD 365.40
Google Vertex AIUSD 35.10USD 70.50USD 513.00
Cloudflare Workers AIUSD 39.60USD 77.55USD 562.50

For the support chatbot, the cheapest price (DeepInfra, USD 14.40 a month) saves USD 12.60 against the median (USD 27.00). For the coding agent the gap is USD 182.25 a month (49% lower). The winner changes with the workload: GMI Cloud wins the cache-heavy agent, DeepInfra the chatbot.

Which Llama 4 Scout 17B 16E Instruct provider is cheapest for your traffic?

GMI Cloud has the lowest input price (USD 0.08) and DeepInfra the lowest output price (USD 0.30). They cost the same at 10 input tokens per output token. With more input than that, as with long prompts or retrieval, GMI Cloud is cheaper; with less, as with long answers, DeepInfra is.

Llama 4 Scout 17B 16E Instruct: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfra (no cache price)USD 0.15 cheapestUSD 0.15 cheapestUSD 0.15 cheapest
GMI Cloud (no cache price)USD 0.185USD 0.185USD 0.185
Novita AI (no cache price)USD 0.2825USD 0.2825USD 0.2825
Amazon Bedrock (no cache price)USD 0.2925USD 0.2925USD 0.2925
Google Vertex AI (no cache price)USD 0.3625USD 0.3625USD 0.3625
Cloudflare Workers AI (no cache price)USD 0.415USD 0.415USD 0.415

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

None of the 6 providers publishes a cached-input discount for Llama 4 Scout 17B 16E Instruct, so cache hits do not change the ranking.

Context windows differ: 1,048,576 tokens at GMI Cloud; 327,680 tokens at DeepInfra; 131,072 tokens at Novita AI. Amazon Bedrock, Google Vertex AI and Cloudflare Workers AI do not state one. The cheapest row is not always the one that fits a long prompt.

What does Llama 4 Scout 17B 16E Instruct cost in other languages?

The same text needs a different number of tokens in each language. With the Llama 4 Maverick tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Llama 4 Scout 17B 16E Instruct:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.017GMI Cloud
Arabic MSAUSD 0.030GMI Cloud
HindiUSD 0.027GMI Cloud
ChineseUSD 0.053GMI Cloud
CodeUSD 0.020GMI Cloud

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

The Meta models whose cheapest standard price is closest to Llama 4 Scout 17B 16E Instruct's (USD 0.15 blended):

Meta models priced closest to Llama 4 Scout 17B 16E Instruct
ModelCheapest inputCheapest outputMax contextProviders
Llama 3.3 70BUSD 0.10USD 0.32131,07214
Llama 3.2 11B Vision InstructUSD 0.16USD 0.16—3
Llama 3.2 3B InstructUSD 0.0509USD 0.335128,0004
Llama 3 8B InstructUSD 0.0925USD 0.0958,1923
Llama 3.2 1B InstructUSD 0.027USD 0.20132,7683
Llama 4 Maverick 17B 128E Instruct FP8USD 0.25USD 0.801,048,5767

Priced closest from other makers: Mistral Small 3.1 24B Instruct (Mistral AI, USD 0.15) · Step-3.5-Flash (StepFun, USD 0.15) · Ministral 3 8B (Mistral AI, USD 0.15).

Compare Llama 4 Scout 17B 16E Instruct with

Also compared: vs Gemma 4 31B.

Every Llama 4 Scout 17B 16E Instruct price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Llama 4 Scout 17B 16E Instruct API cost per token?

From USD 0.08 per 1M input tokens (USD 0.00000008 per token) and USD 0.30 per 1M output tokens (USD 0.0000003 per token) at the lowest standard prices we found, which can come from different providers. The median of 6 standard prices is USD 0.175 input and USD 0.625 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Llama 4 Scout 17B 16E Instruct?

Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.15 per 1M). For input alone the lowest price is USD 0.08 (GMI Cloud); for output alone, USD 0.30 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Meta sell Llama 4 Scout 17B 16E Instruct on its own API?

Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. The lowest-priced host we checked is DeepInfra at USD 0.10 / USD 0.30 per 1M tokens.

Does Llama 4 Scout 17B 16E Instruct have cached input pricing?

None of the 6 standard prices includes a cached-input price, so budget repeated prompts at the full input price.

What is the Llama 4 Scout 17B 16E Instruct context window?

Up to 1,048,576 tokens. 2 standard prices come with less, down to 131,072 tokens (Novita AI and DeepInfra). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on Llama 4 Scout 17B 16E Instruct?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 189.00 a month at GMI Cloud, USD 371.25 at the median price and USD 562.50 at Cloudflare Workers AI. Try your own numbers.

Is there a batch, flex or priority price for Llama 4 Scout 17B 16E Instruct?

Yes: batch from Amazon Bedrock at USD 0.085 / USD 0.33; flex / spot from DeepInfra at USD 0.08 / USD 0.24; priority from DeepInfra at USD 0.15 / USD 0.45 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Llama 4 Scout 17B 16E Instruct free to use through an API?

No provider in our data lists a free price for Llama 4 Scout 17B 16E Instruct as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is Llama 4 Scout 17B 16E Instruct open source, with open weights, and what is its licence?

Meta publishes the weights on Hugging Face as meta-llama/Llama-4-Scout-17B-16E-Instruct, with gated access: Hugging Face asks you to request access and accept the terms before you download. The licence, as the Meta model card states it: Llama 4 Community License Agreement (custom commercial license). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Meta's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does Llama 4 Scout 17B 16E Instruct have?

Total parameters, as the Meta model card states them: 109B. Active parameters per token: 17B. (checked 2026-11-16; BroadNet did not verify these figures.)

How do I call Llama 4 Scout 17B 16E Instruct with the OpenAI SDK?

BroadNet does not serve Llama 4 Scout 17B 16E Instruct. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: DeepInfra (https://api.deepinfra.com/v1/openai, model meta-llama/Llama-4-Scout-17B-16E-Instruct). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity