Llama 4 Scout (Groq)

BudgetOpen weights

GroqChatmeta-llama/llama-4-scout-17b-16e-instruct

Multimodal open-weights Llama at ~600 tokens/sec — vision + tools at budget price.

~594 tokens/sec on Groq LPUs; 8,192 max completion tokens on this hosting.

Capabilities

Tool callingVisionJSON mode

Recommended for

budget vision + tools
multimodal at volume
agent loops

Using this model through Conduix

Call it by its id, or let a routing alias pick it as part of a governed, cross-provider chain with automatic failover.

Direct model idmeta-llama/llama-4-scout-17b-16e-instruct

Not currently part of a routing alias — request it by id.

Get started

Conduix is OpenAI-API-compatible — point any OpenAI SDK at https://api.conduix.ai/v1 and pass meta-llama/llama-4-scout-17b-16e-instruct as the model.

from conduix import Conduix

client = Conduix(api_key="cx_live_YOUR_KEY")  # base URL is built in

response = client.chat.completions.create(
    model="meta-llama/llama-4-scout-17b-16e-instruct",
    messages=[{"role": "user", "content": "Hello, Conduix!"}],
)
print(response.choices[0].message.content)

Tool calling: Pass a tools array and the model calls your functions.
Vision: Accepts image inputs — add image_url parts to a message.
JSON mode: Set response_format for guaranteed-valid JSON output.

The response's x-conduix-model-served header tells you exactly which model answered. See the quickstart for keys, headers, and usage.