Meta (Hosted) Open Weights Live Rates • September 2026

Llama 4 Scout Pricing & Token Economics

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.

Context Window 1.3M
Max Completion 16K Tokens
Inference Speed Ultra Fast
CostRatio Score A+

Normalized Token Pricing Matrix

Real-time input, completion, and cache rates normalized to $/1M tokens.

📥 Prompt Tokens
$ 0.10 / 1M tokens

Cost for prompts, instructions, document retrieval, and system context sent into the model.

~$0.0001 per 1K tokens
📤 Completion Tokens
$ 0.30 / 1M tokens

Cost for generated text, code, tool calls, and structured JSON responses returned by the model.

~$0.0003 per 1K tokens
⚡ Prompt Caching

Standard rates apply. No separate prompt cache discount published via public API routes.

Standard Rates
⚖️ 3:1 Blended Benchmark
$ 0.150 / 1M tokens

Standard industry benchmark assuming 75% prompt reads and 25% completion generation.

Weighted Benchmark

Llama 4 Scout Monthly Bill Estimator

Estimated monthly costs across four standardized enterprise and developer workloads.

Workload Scenario Monthly Token Volume Standard Bill With Prompt Caching
💬
Customer Support Chatbot
10M prompt tokens + 2.5M output tokens per month
12.5M tokens (10M in / 2.5M out) $1.75/mo
📑
Document Analysis & RAG
30M prompt tokens (PDFs/context) + 3M output summaries
33.0M tokens (30M in / 3M out) $3.90/mo
💻
Coding Agent / IDE Swarm
60M prompt tokens (repo context) + 15M code completions
75.0M tokens (60M in / 15M out) $10.50/mo
🤖
Enterprise Agentic Workflow
120M prompt tokens (reasoning loops) + 30M output actions
150.0M tokens (120M in / 30M out) $21.00/mo

Need custom token inputs or prompt volumes?

Use our interactive multi-model token calculator to test exact prompt and completion sliders.

Open Interactive Token Calculator →

Architecture & Capabilities

Technical parameters, supported modalities, and optimal developer use cases.

🎯 Recommended Use Cases

Edge inference, local desktop assistants, low-resource on-device processing

Supported Modalities

📝 Text 👁️ Vision & Images 🛠️ Function / Tool Calling

📐 Context & Output Limits

  • Maximum Context Window: 1,310,720 tokens (1.3M)
  • Maximum Output Length: 16,384 tokens
  • Speed / Latency Tier: Ultra Fast
  • Official Provider: Meta (Hosted)

Frequently Asked Questions

Everything you need to know about Llama 4 Scout API pricing and token calculations.

How much does Llama 4 Scout cost per 1M tokens?

Llama 4 Scout charges $0.10 per 1M input tokens and $0.30 per 1M output tokens. For standard balanced workloads (3:1 input:output ratio), the effective blended rate is $0.150/1M tokens.

Does Llama 4 Scout support prompt caching?

Standard prompt rates apply. Llama 4 Scout does not offer a separate discounted prompt caching tier via standard public endpoints.

What is Llama 4 Scout's maximum context window?

Llama 4 Scout supports up to 1,310,720 tokens (1.3M) in its context window, allowing you to ingest large files and multi-turn chat history with up to 16,384 tokens generated per response.

How does Llama 4 Scout compare to other models?

With a CostRatio rating of A+, Llama 4 Scout provides competitive token economics for open weights tasks. Review the peer comparison table above to compare input and completion rates directly against alternative models.

Explore all latest-generation models and interactive calculators

View Full AI Model Matrix →