Menu

logo
Artificial Analysis
HOME
logo

Llama 3.1 405B: API Provider Benchmarking & Analysis

Analysis of API providers for Llama 3.1 Instruct 405B across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Microsoft Azure, Hyperbolic, Amazon Bedrock, Together.ai, Google, Fireworks, Deepinfra, Replicate, Nebius, Databricks, and SambaNova.
For comparison of Llama 3.1 405B to other models, see
Owner:
Meta
License:
Open
Context window:
128k
Link:

Comparison Summary

Output Speed (tokens/s):Llama 3.1 405B, SambaNova logo SambaNova (164 t/s) and  Llama 3.1 405B, Fireworks logo Fireworks (75 t/s) are the fastest providers of Llama 3.1 405B, followed by  Llama 3.1 405B Turbo, Together.ai logo Llama 3.1 405B Turbo, Together.ai,  Llama 3.1 405B Latency Optimized, Amazon logo Llama 3.1 405B Latency Optimized, Amazon &  Llama 3.1 405B Base, Nebius logo Llama 3.1 405B Base, Nebius.Latency (TTFT):Llama 3.1 405B Vertex, Google logo Google Vertex (0.42s) and  Llama 3.1 405B, Azure logo Azure (0.52s) have the lowest latency for Llama 3.1 405B, followed by  Llama 3.1 405B, Fireworks logo Llama 3.1 405B, Fireworks,  Llama 3.1 405B, Deepinfra logo Llama 3.1 405B, Deepinfra &  Llama 3.1 405B, SambaNova logo Llama 3.1 405B, SambaNova.Blended Price ($/M tokens):Llama 3.1 405B Base, Nebius logo Nebius Base ($1.50) and  Llama 3.1 405B, Deepinfra logo Deepinfra ($1.79) are the most cost-effective providers for Llama 3.1 405B, followed by  Llama 3.1 405B Standard, Amazon logo Llama 3.1 405B Standard, Amazon,  Llama 3.1 405B Latency Optimized, Amazon logo Llama 3.1 405B Latency Optimized, Amazon &  Llama 3.1 405B, Fireworks logo Llama 3.1 405B, Fireworks.Input Token Price:Llama 3.1 405B Base, Nebius logo Nebius Base ($1.00) and  Llama 3.1 405B, Deepinfra logo Deepinfra ($1.79) offer the lowest input token prices for Llama 3.1 405B, followed by  Llama 3.1 405B Standard, Amazon logo Llama 3.1 405B Standard, Amazon,  Llama 3.1 405B Latency Optimized, Amazon logo Llama 3.1 405B Latency Optimized, Amazon &  Llama 3.1 405B, Fireworks logo Llama 3.1 405B, Fireworks.Output Token Price:Llama 3.1 405B, Deepinfra logo Deepinfra ($1.79) and  Llama 3.1 405B Standard, Amazon logo Amazon Standard ($2.40) offer the lowest output token prices for Llama 3.1 405B, followed by  Llama 3.1 405B Latency Optimized, Amazon logo Llama 3.1 405B Latency Optimized, Amazon,  Llama 3.1 405B Base, Nebius logo Llama 3.1 405B Base, Nebius &  Llama 3.1 405B, Fireworks logo Llama 3.1 405B, Fireworks.

Highlights

Quality
Artificial Analysis Quality Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:

Summary Analysis

Output Speed vs. Price

Output Speed: 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: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Latency vs. Output Speed

Latency: Seconds to First Token Received; Output Speed: Output Tokens per Second
Most attractive quadrant
Size represents Price (USD per M Tokens)
Output Speed: 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).
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Context Window

Context Window: Tokens Limit; Higher is better
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Variance between providers: While models have their own context window, in cases this is limited by providers.

Pricing: Input and Output Prices

USD per 1M Tokens; Lower is better
Input price
Output price
Input price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Output price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output Tokens per Second; Higher is better
Output Speed: 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).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Output Speed Variance

Output Tokens per Second; Results by percentile; Higher is better
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
Output Speed: 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).
Boxplot: Shows variance of measurements
Picture of the author
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Output Speed, Over Time

Output Tokens per Second; Higher is better
Smaller, emerging providers offer high output speed, though precise speeds delivered vary day-to-day.
Output Speed: 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).
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Output Speed by Input Token Count (Context Length)

Output Tokens per Second; Higher is better
100 input tokens
1k input tokens
10k input tokens
100k input tokens
Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.
Output Speed: 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).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Latency

Measured by Time (seconds) to First Token

Latency

Seconds to First Token Received; Lower is better
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.

Latency Variance

Seconds to First Token Received; Results by percentile; Lower median is better
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Boxplot: Shows variance of measurements
Picture of the author

Latency, Over Time

Seconds to First Token Received; Lower is better
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

Latency by Input Token Count (Context Length)

Seconds to First Token Received; Lower is better
100 input tokens
1k input tokens
10k input tokens
100k input tokens
Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.

Total Response Time

Time to receive 100 tokens output, calculated from latency and output speed metrics

Total Response Time vs. Price

Total Response Time: End-to-End Seconds to Output 100 Tokens; Price: USD per 1M Tokens
Most attractive quadrant
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.

Total Response Time

End-to-End Seconds to Output 100 Tokens; Lower is better
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.

Total Response Time, Over Time

End-to-End Seconds to Output 100 Tokens; Lower is better
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Total Response Time by Input Token Count (Context Length)

End-to-End Seconds to Output 100 Tokens; Lower is better
100 input tokens
1k input tokens
10k input tokens
100k input tokens
Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Median: Figures represent median (P50) measurement over the past 14 days or otherwise to reflect sustained changes in performance.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Llama 3.1 405B, SambaNova: 8k context

Quality & Capabilities

Quality Evaluations (Preliminary Results)

Evaluation results measured independently by Artificial Analysis; Higher is better
Artificial Analysis Quality Index
Reasoning & Knowledge (MMLU)
Quantitative Reasoning (MATH-500)
Coding (HumanEval)
Artificial Analysis Quality Index: Represents the the average of each provider's results across evaluations.

API Features

API Features: Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Replicate logoReplicate
Hyperbolic logoHyperbolic
Amazon Standard logoAmazon Standard
Amazon Latency Optimized logoAmazon Latency Optimized
Nebius Base logoNebius Base
Google Vertex logoGoogle Vertex
Azure logoAzure
Fireworks logoFireworks
Deepinfra logoDeepinfra
SambaNova logoSambaNova
Databricks logoDatabricks
Together.ai Turbo logoTogether.ai Turbo
Function (Tool) Calling: Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.
JSON Mode: Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

Summary Table of Key Comparison Metrics

Features
Price
Output tokens/s
Latency
Replicate logo
Meta logo
Llama 3.1 405B
128k
74
$9.50
18.7
0.92
Hyperbolic logo
Meta logo
Llama 3.1 405B
128k
75
$4.00
16.3
0.79
Amazon Bedrock Standard logo
Meta logo
Llama 3.1 405B Standard
128k
74
$2.40
13.3
1.78
Amazon Bedrock Latency Optimized logo
Meta logo
Llama 3.1 405B Latency Optimized
128k
74
$3.00
62.7
0.84
Nebius Base logo
Meta logo
Llama 3.1 405B Base
128k
74
$1.50
33.9
0.75
Google Vertex logo
Meta logo
Llama 3.1 405B Vertex
128k
74
$7.75
28.9
0.42
Microsoft Azure logo
Meta logo
Llama 3.1 405B
128k
74
$8.00
21.9
0.52
Fireworks logo
Meta logo
Llama 3.1 405B
128k
73
$3.00
74.8
0.60
Deepinfra logo
Meta logo
Llama 3.1 405B
33k
73
$1.79
23.0
0.71
SambaNova logo
Meta logo
Llama 3.1 405B
8k
74
$6.25
163.6
0.74
Databricks logo
Meta logo
Llama 3.1 405B
128k
72
$7.50
30.6
0.76
Together.ai Turbo logo
Meta logo
Llama 3.1 405B Turbo
128k
74
$3.50
74.0
0.75