Llama 4 Scout API pricing

11 providers serve Llama 4 Scout. Llama 4 Scout is an open-weight model (Llama 4 Community) with 109B total parameters, 17B active per token (mixture-of-experts), up to 10486K context. Prices below are per 1M tokens, cheapest input first (self-hosting math further down).

Refreshed 2026-08-23 · list prices from provider APIs

Input floor $0.050/1M at Lambda Output floor $0.100/1M at Lambda Find your workload winner →

Provider	Input $/1M	Output $/1M	Cache read $/1M	Context
Lambda	$0.050	$0.100output floor	-	16K	Use
DeepInfra	$0.080	$0.300	-	328K	Use
Nscale	$0.090	$0.290	-	-	Use
Groq	$0.110	$0.340	-	131K	Use
Together AI	$0.180	$0.590	-	-	Use
Novita AI	$0.180	$0.590	-	131K	Use
Azure AI Foundry	$0.200	$0.780	-	10000K	Use
Google Vertex AI	$0.250	$0.700	-	10000K	Use
Cloudflare	$0.270	$0.850	-	131K	Use
SambaNova	$0.400	$0.700	-	8K	Use
Oracle OCI	$0.720	$0.720	-	10486K	Use

The cheapest way to run Llama 4 Scout

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $6.50/month, at Lambda. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. On output-token cost alone, the API floor remains below our self-hosting estimate of ~$0.117/1M. Details below. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Workload preset Input tokens / month (millions) Output tokens / month (millions) Input served from cache %

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Or run it yourself: Llama 4 Scout self-hosting economics

Llama 4 Scout is open-weight (Llama 4 Community), so the API price above competes with the GPU-hour market. 109B total parameters (MoE, ~17B active per token) needs roughly 150 GB VRAM at FP8 or 75 GB at INT4, KV-cache headroom included.

GPU that fits (FP8, single card)	VRAM	From $/hr	Cheapest at
MI300X	192 GB	$0.500community	RunPod	Rent
B200	180 GB	$3.06spot	Verda
B300	288 GB	$3.75spot	Verda
GB300	288 GB	$4.31spot	Verda

Breakeven estimate: a well-batched vLLM deployment on one MI300X ($0.500/hr) at ~2382 aggregate tok/s and 50% utilization works out to roughly $0.117 per 1M output tokens, versus $0.100 via the cheapest output-token API (Lambda). The API is cheaper unless your utilization or throughput beats these assumptions. Planning estimate: throughput varies with hardware, quantization, batch size and context. Tune it in the calculator.

Related models

Model	Cheapest in $/1M	Cheapest out $/1M	Providers
Llama 3.3 70B	$0.100	$0.200	15
Llama 3.1 8B	$0.020	$0.030	15
Llama 3.1 70B Instruct	$0.120	$0.300	10
Llama 4 Maverick	$0.050	$0.100	9
Llama 3.2 3B	$0.020	$0.020	9
Llama-3-70b	$0.120	$0.300	7

FAQ

What is the cheapest API for Llama 4 Scout?

As of 2026-08-23, the lowest input price for Llama 4 Scout is Lambda at $0.050 per 1M input tokens. The lowest output price is Lambda at $0.100 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is DeepInfra at $0.080, a 60% difference.

How much VRAM do you need to self-host Llama 4 Scout?

Llama 4 Scout has 109B parameters, so plan for roughly 150 GB of VRAM at FP8 or 75 GB at INT4/AWQ, KV-cache headroom included. A single MI300X (192 GB) fits it.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON