Meta Llama · LLM API pricing

Llama 4 Scout 17B 16E Instruct API pricing: cheapest provider

7 providers sell Llama 4 Scout 17B 16E Instruct. Lambda is cheapest; the most expensive charges 11.5× as much for the same model.

Cheapest$0.0625per 1M · Lambda
Input · output$0.05 / $0.10per 1M tokens
Price gap11.5×across 7 providers
Accuracy51.8%GPQA
Context10.5Mmax tokens

$0.0625 Lambda11.5× spread$0.72 Oracle Cloud Generative AI

Compare all 7 providers ⇄ Compare with another model

Already paying for Llama 4 Scout 17B 16E Instruct? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Sep 28, 2026 · How we collect and rank prices

Ranked for your volume

Llama 4 Scout 17B 16E Instruct monthly cost by provider

Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.

Input tokens per month (millions)Prompts, context and documents you send.Output tokens per month (millions)Tokens the model generates.

More requirements: caching, context, features, provider

Cached share of input (%)0 = no caching. Only documented cache-read rates qualify.Required context per request (tokens)0 = any. Providers without a sufficient known limit are excluded.Required featureProvider requirement

Provider	Estimated / month	Input / 1M	Output / 1M	Context
1 LambdaInference provider - lowest for your volumePricing page	$0.70	$0.05	$0.10	16,384
2 NscaleInference providerPricing page	$1.48	$0.09	$0.29	Not listed
3 DeepInfraInference providerPricing page	$1.60	$0.10	$0.30	327,680
4 Novita AIInference providerPricing page	$2.98	$0.18	$0.59	131,072
5 Microsoft Azure AI FoundryCloud platformPricing page	$3.56	$0.20	$0.78	10,000,000
6 Cloudflare Workers AICloud platformPricing page	$4.40	$0.27	$0.85	131,000
7 Oracle Cloud Generative AICloud platformPricing page	$8.64	$0.72	$0.72	10,485,760

Order depends on listed price for your volume only. No provider pays for its position.

Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.

Share this comparison as a Markdown table

For a post, a doc or a forum answer. The source line links back here, so readers can check today's prices.

Markdown

| Llama 4 Scout 17B 16E Instruct provider | Input / 1M tokens | Output / 1M tokens | 10M in + 2M out per month |
|---|---:|---:|---:|
| Lambda | $0.05 | $0.10 | $0.70 |
| Nscale | $0.09 | $0.29 | $1.48 |
| DeepInfra | $0.10 | $0.30 | $1.60 |
| Novita AI | $0.18 | $0.59 | $2.98 |
| Microsoft Azure AI Foundry | $0.20 | $0.78 | $3.56 |
| Cloudflare Workers AI | $0.27 | $0.85 | $4.40 |
| Oracle Cloud Generative AI | $0.72 | $0.72 | $8.64 |

Standard list prices as of Oct 31, 2026. Source: [AISelect.online](https://aiselect.online/models/llama-4-scout-17b-16e-instruct)

Accuracy: GPQA Diamond (graduate-level science questions) measured by Epoch AI (CC BY 4.0) on Llama-4-Scout-17B-16E-Instruct, run Apr 8, 2025. The model is the same at every provider, though quantized deployments can score lower.

Price history

The cheapest price has not changed since tracking started on Sep 28, 2026: $0.0625 per 1M tokens at Lambda. All price changes

Switch to the cheapest OpenAI-compatible provider

Switch to Nscale

Already using the OpenAI SDK? Change the base URL, key and model name:

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://inference.api.nscale.com/v1",
    api_key=os.environ["NSCALE_SERVICE_TOKEN"],
)
response = client.chat.completions.create(
    model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
    messages=[{"role": "user", "content": "Hello"}],
)

Base URL from Nscale's API docs, model name from the open pricing datasets. Check the model page in Nscale's docs before you switch production traffic.

Compare Llama 4 Scout 17B 16E Instruct with another model

Or pick any model

Model A

Model B

Before you pick a provider

Context windows differ by provider, from 16K to 10.5M tokens. A cheaper host may not accept your longest prompts.

Keep comparing

More Meta Llama models

Llama-3.3-70B-Instruct, Llama-3.1-8B-Instruct, Llama 3.2 3B Instruct, llama-3.1-70b-instruct, Llama 4 Maverick 17B 128E Instruct FP8, Llama 3.2 11B Vision Instruct, Llama 3.2 1B Instruct, Llama Guard 3 8B

All Meta Llama API prices - All LLM API prices - Watch Llama 4 Scout 17B 16E Instruct prices (RSS) - Methodology