impulse

Llama 4 Scout 17B 128e Instruct

Open weights
API id llama-4-scout-17b-128e-instruct-maas
Input / 1M
$0.25
at Vertex AI
Output / 1M
$0.70
at Vertex AI
Context window
10M
tokens
Max output
10M
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Vertex AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.25$0.70
Batch
50% off
$0.125$0.35

What it costs a month

At Vertex AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$128
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$145
  • Coding agent1,000 requests a day, 40K in / 2K out$342
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$384
Use your own numbers

Where to run it

1 host serve Llama 4 Scout 17B 128e Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
llama-4-scout-17b-128e-instruct-maas
$0.25 / $0.70

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesText
Produces
Text
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Vertex AI.

Smaller Meta models

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    45% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    45% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    28% less

Open-weight picks

  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    3% less
  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    28% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    30% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    51% less

Call it

Using Vertex AI's API.

Python
from litellm import completion

response = completion(
    model="vertex_ai/llama-4-scout-17b-128e-instruct-maas",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama 4 Scout 17B 128e Instruct cost?

On Vertex AI, Llama 4 Scout 17B 128e Instruct costs $0.25 per million input tokens and $0.70 per million output tokens.

Which APIs offer Llama 4 Scout 17B 128e Instruct?

Llama 4 Scout 17B 128e Instruct runs on 1 API: Vertex AI.

What is Llama 4 Scout 17B 128e Instruct's context window?

10M tokens, with up to 10M tokens in one reply.

Is Llama 4 Scout 17B 128e Instruct being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Llama 4 Scout 17B 128e Instruct?

Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (66% less), Claude Haiku 5.5 on Anthropic (45% less), GPT-6 Luna on OpenAI (45% less) and Muse Glimmer 30B on EmpirioLabs AI (3% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Llama 4 Scout 17B 128e Instruct's API model id?

Use llama-4-scout-17b-128e-instruct-maas with Vertex AI.

Sources

Raw catalog entry for llama-4-scout-17b-128e-instruct-maas on Vertex AI
{
  "input_cost_per_token": 2.5e-7,
  "input_cost_per_token_batches": 1.25e-7,
  "litellm_provider": "vertex_ai-llama_models",
  "max_input_tokens": 10000000,
  "max_output_tokens": 10000000,
  "mode": "chat",
  "output_cost_per_token": 7e-7,
  "output_cost_per_token_batches": 3.5e-7,
  "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text",
    "code"
  ],
  "supports_function_calling": true,
  "supports_tool_choice": true
}