Last refreshed 2026-07-09. Next refresh: weekly.
Why use Llama 4 Scout 17B-16E Instruct on Vercel AI Gateway?
Vercel AI Gateway offers Llama 4 Scout 17B-16E Instruct with pay-as-you-go pricing at $0.17/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Llama 4 Scout 17B-16E Instruct across 12 providers to find the best fit for your use caseInput / 1M
$0.17
Output / 1M
$0.66
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
meta/llama-4-scoutRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="meta/llama-4-scout",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "meta/llama-4-scout", not the LLMReference slug "llama-4-scout-17b-16e-instruct".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Llama 4 Scout 17B-16E Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | $0.27 | $0.85 |
| OpenRouter | $0.08 | $0.30 |
| Together AI | — | — |
| Fireworks AI | — | — |
| DeepInfra | $0.08 | $0.30 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.17 |
| Output tokens | $0.66 |
Capabilities
VisionMultimodalStructured Outputs
About Llama 4 Scout 17B-16E Instruct
Meta's Llama 4 Scout is a 17-billion parameter mixture-of-experts model with 16 expert routing. Optimized for efficient inference on edge and cloud environments with strong multi-turn conversation capabilities. Available on Cloudflare Workers AI.
Get Started
Model Specs
Released2025-04-05
Parameters109B (17B active)
Context10m
ArchitectureMixture of Experts
Knowledge cutoff2024-08