Skip to content

Meta: Llama 4 Scout provider comparison

meta-llama/llama-4-scout

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. It supports native multimodal input...

Endpoints:
4
Context:
10M
Input:
text, image
Output:
text
Compare this model in a set →

At a glance

Comparison winners

Based on 1,000 input and 500 output tokens using the latest published median speed data.

Best cost/speed trade-off

DeepInfradeepinfra/fp8

$0.1667 / 1M tokens

15.49 s estimated response

Cheapest

DeepInfradeepinfra/fp8

$0.1667 / 1M tokens

$0.00025 for the sample request

Fastest

Google Vertexgoogle-vertex/us-east5

9.16 s estimated response

$0.4 / 1M tokens

Visual comparison

Price and performance charts

Compare published endpoint pricing and estimated response time visually.

Effective price by endpoint

USD per 1 million tokens for input and output. Lower is better.

DeepInfra has the lowest estimated cost for 1,000 input and 500 output tokens at $0.00025.

Estimated cost vs. response time

Based on 1,000 input and 500 output tokens. Cost is shown in USD per 1 million tokens. Lower and further left is better; the single best cost/speed trade-off appears at full opacity.

4 providers have complete pricing and speed data. DeepInfra is closest to the ideal combination of lowest cost and fastest response.

Server-rendered comparison

Provider endpoints

Prompt and completion prices are effective USD per token as published by OpenRouter. Missing speed data never removes an endpoint.

Endpoint comparison for Meta: Llama 4 Scout
Provider / routeCurrent pricing ↗Speed measurementsEndpoint details
Provider / route
DeepInfradeepinfra/fp8
CheapestBest cost/speed trade-off
Current pricing
Input price
$0.1 / 1M tokens
Output price
$0.3 / 1M tokens
Sample cost
$0.00025
Speed measurements
500-token response
15.49 s
Response starts
0.34 s
Output speed
33.0 tok/s
Endpoint details
Uptime (30 min)
99.96%
Context
327.7K
Model format
fp8
Max output
16.4K
13 parameters

frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p

Provider / route
Groqgroq
Current pricing
Input price
$0.11 / 1M tokens
Output price
$0.34 / 1M tokens
Sample cost
$0.00028
Speed measurements
500-token response
19.44 s
Response starts
0.20 s
Output speed
26.0 tok/s
Endpoint details
Uptime (30 min)
99.73%
Context
131.1K
Model format
unknown
Max output
8.2K
9 parameters

max_tokens, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p

Provider / route
NovitaAInovita/bf16
Current pricing
Input price
$0.18 / 1M tokens
Output price
$0.59 / 1M tokens
Sample cost
$0.000475
Speed measurements
500-token response
16.64 s
Response starts
0.51 s
Output speed
31.0 tok/s
Endpoint details
Uptime (30 min)
100.00%
Context
131.1K
Model format
bf16
Max output
131.1K
9 parameters

frequency_penalty, max_tokens, presence_penalty, repetition_penalty, seed, stop, temperature, top_k, top_p

Provider / route
Google Vertexgoogle-vertex/us-east5
Fastest
Current pricing
Input price
$0.25 / 1M tokens
Output price
$0.7 / 1M tokens
Sample cost
$0.0006
Speed measurements
500-token response
9.16 s
Response starts
0.68 s
Output speed
59.0 tok/s
Endpoint details
Uptime (30 min)
99.85%
Context
1.3M
Model format
unknown
Max output
8.2K
12 parameters

frequency_penalty, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p

Endpoint data fetched .

Llama 4 Scout deployment guide

How to choose a Llama 4 Scout inference provider

Llama 4 Scout is indexed here as a text model by Meta, with 4 provider endpoints from DeepInfra, Groq, NovitaAI, Google Vertex. The comparison preserves each exact OpenRouter routing tag so pricing and performance observations can be connected to the route an application would actually request.

Match the endpoint to the workload

The model publishes a 10M-token context window. It accepts text, image input and returns text output. 15 distinct supported parameters appear across the listed routes. Confirm limits on the specific endpoint rather than assuming every host exposes the same configuration.

Compare the real request economics

DeepInfra currently has the lowest estimated cost for the standard 1,000-input/500-output-token sample at $0.00025. Input-heavy and output-heavy applications can produce a different result, so review both per-million-token prices in the endpoint table.

Balance response start and generation speed

Google Vertex currently has the shortest estimated 500-token response at 9.16 seconds. DeepInfra is the single endpoint closest to the current ideal cost/speed combination. Recent observations can change, so validate finalists with your own prompts.