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, Amazon Bedrock, Hyperbolic, Together.ai, Google, Fireworks, Deepinfra, Replicate, Nebius, Databricks, and SambaNova.
Comparison Summary
Output Speed (tokens/s):
SambaNova (166 t/s) and 
Together.ai Turbo (80 t/s) are the fastest providers of Llama 3.1 405B, followed by 
Llama 3.1 405B, Fireworks, 
Llama 3.1 405B Base, Nebius & 
Llama 3.1 405B Vertex, Google.Latency (TTFT): Google Vertex (0.42s) and 
Deepinfra (0.53s) have the lowest latency for Llama 3.1 405B, followed by 
Llama 3.1 405B, Azure, Llama 3.1 405B, Fireworks & Llama 3.1 405B Turbo, Together.ai.Blended Price ($/M tokens): Nebius Base ($1.50) and Deepinfra ($1.79) are the most cost-effective providers for Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Turbo, Together.ai & 
Llama 3.1 405B, Hyperbolic.Input Token Price: Nebius Base ($1.00) and Deepinfra ($1.79) offer the lowest input token prices for Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Turbo, Together.ai & Llama 3.1 405B, Hyperbolic.Output Token Price: Deepinfra ($1.79) and Nebius Base ($3.00) offer the lowest output token prices for Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Turbo, Together.ai & Llama 3.1 405B, Hyperbolic.
SambaNova (166 t/s) and Together.ai Turbo (80 t/s) are the fastest providers of Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Base, Nebius & Llama 3.1 405B Vertex, Google.Latency (TTFT): Google Vertex (0.42s) and Deepinfra (0.53s) have the lowest latency for Llama 3.1 405B, followed by Llama 3.1 405B, Azure, Llama 3.1 405B, Fireworks & Llama 3.1 405B Turbo, Together.ai.Blended Price ($/M tokens): Nebius Base ($1.50) and Deepinfra ($1.79) are the most cost-effective providers for Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Turbo, Together.ai & Llama 3.1 405B, Hyperbolic.Input Token Price: Nebius Base ($1.00) and Deepinfra ($1.79) offer the lowest input token prices for Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Turbo, Together.ai & Llama 3.1 405B, Hyperbolic.Output Token Price: Deepinfra ($1.79) and Nebius Base ($3.00) offer the lowest output token prices for Llama 3.1 405B, followed by Llama 3.1 405B, Fireworks, Llama 3.1 405B Turbo, Together.ai & Llama 3.1 405B, Hyperbolic.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:
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)
Coding (HumanEval)
Artificial Analysis Quality Index: Represents the the average of each provider's results across evaluations.
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.
Summary Analysis
Output Speed vs. Price
Output Speed: Output Tokens per Second; Price: Price: USD per 1M Tokens
Most attractive quadrant
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
Pricing
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
Pricing: Cached Input Tokens
| Models | Cache Pricing Notes |
|---|---|
| Google Vertex |
|
Pricing Cached Input Tokens: Some providers offer a caching layer for input tokens, which can help reduce API usage costs.
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
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
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
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: Seconds to Output 100 Tokens; Price: 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
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
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)
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
API Features
API Features: Function (Tool) Calling & JSON Mode
ReplicateFunction (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 | |||
|---|---|---|---|---|---|---|
 | Llama 3.1 405B | 128k | 72 | $9.50 | 18.6 | 0.89 |
 | Llama 3.1 405B | 128k | 74 | $4.00 | 16.6 | 0.89 |
 | Llama 3.1 405B | 128k | 72 | $7.99 | 13.0 | 1.77 |
 | Llama 3.1 405B Base | 128k | 72 | $1.50 | 33.7 | 0.83 |
 | Llama 3.1 405B Vertex | 128k | 72 | $7.75 | 29.5 | 0.42 |
 | Llama 3.1 405B | 128k | 72 | $8.00 | 17.0 | 0.54 |
 | Llama 3.1 405B | 128k | 72 | $3.00 | 78.1 | 0.55 |
 | Llama 3.1 405B | 33k | 72 | $1.79 | 18.6 | 0.53 |
 | Llama 3.1 405B | 8k | 74 | $6.25 | 166.2 | 1.51 |
 | Llama 3.1 405B Turbo | 128k | 72 | $3.50 | 79.7 | 0.70 |