Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Log in
Llama 4 Scout logo

Llama 4 Scout API Provider Benchmarking & Analysis

Meta

Open weights model

Released April 2025

Analysis of API providers for Llama 4 Scout across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Eigen AI, Google Vertex, Microsoft Azure, CompactifAI, Amazon Bedrock, Weights & Biases, Cloudflare, Groq, DeepInfra, Novita.

Fastest

#1
Eigen AIEigen AI
506.4 t/s
#2
GroqGroq
401.5 t/s
#3
AmazonAmazon
298.6 t/s
#4
Google VertexGoogle Vertex
270.5 t/s
#5
AzureAzure
199.2 t/s

Output speed

Total 10 providers

Lowest Latency

#1
CompactifAICompactifAI
0.24 s
#2
GroqGroq
0.29 s
#3
Google VertexGoogle Vertex
0.40 s
#4
AmazonAmazon
0.44 s
#5
Weights & BiasesWeights & Biases
0.44 s

Time to first token

Total 10 providers

Lowest Price

#1
CompactifAICompactifAI
$0.11
#2
DeepInfraDeepInfra
$0.14
#3
GroqGroq
$0.17
#4
NovitaNovita
$0.28
#5
AmazonAmazon
$0.29

Blended price (per 1M tokens)

Total 10 providers

Llama 4 Scout is available through 10 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For output speed, the top providers are Eigen AI (506.4 t/s), Groq (401.5 t/s), Amazon (298.6 t/s). Speed varies significantly across providers, with a 154% difference between the fastest and slowest.
  • For latency, CompactifAI (0.24s), Groq (0.29s), Google Vertex (0.40s) offer the lowest time to first token.
  • For pricing, CompactifAI (0.11), DeepInfra (0.14), Groq (0.17) offer the lowest blended prices per 1M tokens. Prices vary up to 2.7x across providers.
  • CompactifAI offers both the lowest latency and best pricing, making it attractive for cost-conscious applications. Eigen AI is the fastest option for throughput-intensive workloads.
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better

Navigation

PricingSpeedLatencyEnd-to-End Response TimeAPI FeaturesSummary Table of Key Comparison Metrics
Parallel Queries:
Prompt Length:

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above!

Pricing

Pricing: Input and Output Prices

USD per 1M Tokens; Lower is better
Input price
Output price

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Speed vs. Price

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens
Most attractive quadrant
Amazon
Azure
Cloudflare
CompactifAI
DeepInfra
Eigen AI
Google Vertex
Groq
Novita
Weights & Biases

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output Tokens per Second; Higher is better; 1,000 Input Tokens (Coding workload)

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Latency vs. Output Speed

Latency: Seconds to First Token Received; Output Speed: Output Tokens per Second; 1,000 Input Tokens (Coding workload)
Most attractive quadrant
Size represents Price (USD per M Tokens)
Amazon
Azure
Cloudflare
CompactifAI
DeepInfra
Eigen AI
Google Vertex
Groq
Novita
Weights & Biases

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Latency

Measured by Time (seconds) to First Token

Time to First Token

Seconds to First Token Received; Lower is better; 1,000 Input Tokens (Coding workload)

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

End-to-End Response Time

Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better; 1,000 Input Tokens (Coding workload)
Input processing time
'Thinking' time (reasoning models)
Outputting time

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

API Features

Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Eigen AI logoEigen AI
Google Vertex logoGoogle Vertex
Azure logoAzure
CompactifAI logoCompactifAI
Amazon logoAmazon
Weights & Biases logoWeights & Biases
Cloudflare logoCloudflare
Groq logoGroq
DeepInfra logoDeepInfra
Novita logoNovita

Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.

Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

Context Window

Context Window: Tokens Limit; Higher is better

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

While models have their own context window, in cases this is limited by providers.

Summary Table of Key Comparison Metrics

Frequently Asked Questions

Common questions about Llama 4 Scout providers

Llama 4 Scout is available through 10 API providers: Eigen AI, Google Vertex, Azure, CompactifAI, Amazon, Weights & Biases, Cloudflare, Groq, DeepInfra, and Novita. Each provider offers different performance characteristics and pricing.

Llama 4 Scout is currently available through 10 API providers that we benchmark and track.

The fastest providers for Llama 4 Scout by output speed are Eigen AI (506.4 t/s), Groq (401.5 t/s), and Amazon (298.6 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for Llama 4 Scout are CompactifAI (0.24s), Groq (0.29s), and Google Vertex (0.40s). Lower latency means faster initial response time.

The most affordable providers for Llama 4 Scout by blended price are CompactifAI ($0.11 per 1M tokens), DeepInfra ($0.14 per 1M tokens), and Groq ($0.17 per 1M tokens). Blended price uses a 3:1 input to output token ratio.

The providers with the lowest input token pricing for Llama 4 Scout are DeepInfra ($0.08 per 1M input tokens), CompactifAI ($0.10 per 1M input tokens), and Groq ($0.11 per 1M input tokens).

The providers with the lowest output token pricing for Llama 4 Scout are CompactifAI ($0.14 per 1M output tokens), DeepInfra ($0.30 per 1M output tokens), and Groq ($0.34 per 1M output tokens).

Prices for Llama 4 Scout vary up to 3.8x across providers. The most affordable is CompactifAI at $0.11 per 1M tokens, while Cloudflare charges $0.41 per 1M tokens.

Output speed for Llama 4 Scout varies significantly across providers. Eigen AI is the fastest at 506.4 t/s, which is 7.1x faster than DeepInfra at 71.6 t/s.

6 of 10 providers support JSON mode for Llama 4 Scout: Eigen AI, Google Vertex, Azure, CompactifAI, Weights & Biases, and Groq.

8 of 10 providers support function calling for Llama 4 Scout: Google Vertex, CompactifAI, Amazon, Weights & Biases, Cloudflare, Groq, DeepInfra, and Novita.

The best provider for Llama 4 Scout depends on your priorities: Eigen AI offers the highest output speed, CompactifAI has the lowest latency, and CompactifAI provides the most competitive pricing.

When choosing a provider for Llama 4 Scout, consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about Llama 4 Scout's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview