Llama 4 Maverick: API Provider Performance Benchmarking & Price Analysis

	Features	Model Intelligence	Price	Output tokens/s	Latency	End-to-End Response Time
Llama 4 Maverick (FP8)	1m	42	$0.28	131.8	0.22	4.02	N/A
Llama 4 Maverick (FP8)	1m	42	$0.35	125.3	0.37	4.36	N/A
Llama 4 Maverick	32k	42	$0.30	2,261.8	0.27	0.49	N/A
Llama 4 Maverick	128k	42	$0.42	270.4	0.61	2.46	N/A
Llama 4 Maverick Vertex	524k	42	$0.55	250.2	0.32	2.32	N/A
Llama 4 Maverick (FP8)	128k	42	$0.61	142.4	0.34	3.85	N/A
Llama 4 Maverick (Base)	1m	42	$0.39	25.6	2.37	21.93	N/A
Llama 4 Maverick (FP8)	1m	42	$0.26	72.9	0.25	7.10	N/A
Llama 4 Maverick (Turbo, FP8)	8k	42	$0.50	830.7	0.21	0.81	N/A
Llama 4 Maverick (FP8)	1m	42	$0.34	80.6	0.45	6.65	N/A
Llama 4 Maverick (FP8)	1m	42	$0.39	146.5	0.70	4.11	N/A
Llama 4 Maverick	131k	42	$0.30	505.8	0.18	1.17	N/A
Llama 4 Maverick	131k	42	$0.92	690.6	0.35	1.07	N/A
Llama 4 Maverick	1m	42	$0.41	82.1	0.22	6.31	N/A

	Features	Model Intelligence	Price	Output tokens/s	Latency	End-to-End Response Time
Llama 4 Maverick (FP8)	1m	42	$0.28	131.8	0.22	4.02	N/A
Llama 4 Maverick (FP8)	1m	42	$0.35	125.3	0.37	4.36	N/A
Llama 4 Maverick	32k	42	$0.30	2,261.8	0.27	0.49	N/A
Llama 4 Maverick	128k	42	$0.42	270.4	0.61	2.46	N/A
Llama 4 Maverick Vertex	524k	42	$0.55	250.2	0.32	2.32	N/A
Llama 4 Maverick (FP8)	128k	42	$0.61	142.4	0.34	3.85	N/A
Llama 4 Maverick (Base)	1m	42	$0.39	25.6	2.37	21.93	N/A
Llama 4 Maverick (FP8)	1m	42	$0.26	72.9	0.25	7.10	N/A
Llama 4 Maverick (Turbo, FP8)	8k	42	$0.50	830.7	0.21	0.81	N/A
Llama 4 Maverick (FP8)	1m	42	$0.34	80.6	0.45	6.65	N/A
Llama 4 Maverick (FP8)	1m	42	$0.39	146.5	0.70	4.11	N/A
Llama 4 Maverick	131k	42	$0.30	505.8	0.18	1.17	N/A
Llama 4 Maverick	131k	42	$0.92	690.6	0.35	1.07	N/A
Llama 4 Maverick	1m	42	$0.41	82.1	0.22	6.31	N/A

Output Speed vs. Price: Llama 4 Maverick Providers

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens

Most attractive quadrant

Amazon

Azure (FP8)

Cerebras

Deepinfra (FP8)

Deepinfra (Turbo, FP8)

Fireworks (Base)

GMI (FP8)

Google Vertex

Groq

Lambda (FP8)

Novita (FP8)

Parasail (FP8)

SambaNova

Together.ai

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 72 hours to reflect sustained changes in performance.

Notes: Llama 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Latency vs. Output Speed: Llama 4 Maverick Providers

Latency: Seconds to First Token Received; Output Speed: Output Tokens per Second; 1,000 Input Tokens

Most attractive quadrant

Size represents Price (USD per M Tokens)

Amazon

Azure (FP8)

Cerebras

Deepinfra (FP8)

Deepinfra (Turbo, FP8)

Fireworks (Base)

GMI (FP8)

Google Vertex

Groq

Lambda (FP8)

Novita (FP8)

Parasail (FP8)

SambaNova

Together.ai

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): 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: 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 72 hours to reflect sustained changes in performance.

Notes: Llama 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Context Window: Llama 4 Maverick Providers

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: Llama 4 Maverick Providers

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 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Output Speed: Llama 4 Maverick Providers

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 72 hours to reflect sustained changes in performance.

Notes: Llama 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Output Speed Variance: Llama 4 Maverick Providers

Output Tokens per Second; Results by percentile; Higher is better; 1,000 Input Tokens

Median; other points represent Min, 25th, 75th percentiles and Max 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 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Output Speed by Input Token Count (Context Length): Llama 4 Maverick Providers

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 72 hours to reflect sustained changes in performance.

Notes: Llama 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Time to First Token: Llama 4 Maverick Providers

Seconds to First Token Received; Lower is better; 1,000 Input Tokens

Latency (Time to First Token): 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.

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

Time to First Token Variance: Llama 4 Maverick Providers

Seconds to First Token Received; Results by percentile; Lower median is better; 1,000 Input Tokens

Median; other points represent Min, 25th, 75th percentiles and Max respectively

Latency (Time to First Token): 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.

Boxplot: Shows variance of measurements

Latency by Input Token Count (Context Length): Llama 4 Maverick Providers

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): 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.

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

End-to-End Response Time vs. Price: Llama 4 Maverick Providers

End-to-End Response Time: End-to-End Seconds to Output 500 Tokens; Price: USD per 1M Tokens

Most attractive quadrant

Amazon

Azure (FP8)

Cerebras

Deepinfra (FP8)

Deepinfra (Turbo, FP8)

Fireworks (Base)

GMI (FP8)

Google Vertex

Groq

Lambda (FP8)

Novita (FP8)

Parasail (FP8)

SambaNova

Together.ai

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

End-to-End Response Time: Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and output speed.

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

End-to-End Response Time: Llama 4 Maverick Providers

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better; 1,000 Input Tokens

'Thinking' time (reasoning models)

Input processing time

Outputting time

End-to-End Response 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

Standardized Reasoning Tokens: 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.

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

End-to-End Response Time by Input Token Count (Context Length): Llama 4 Maverick Providers

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; 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.

End-to-End Response Time: Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and output speed.

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

Notes: Llama 4 Maverick (FP8), Parasail: 1m context, Llama 4 Maverick, Cerebras: 32k context, Llama 4 Maverick, Amazon: 128k context, Llama 4 Maverick Vertex, Google: 524k context, Llama 4 Maverick (FP8), Azure: 128k context, Llama 4 Maverick (Base), Fireworks: 1m context, Llama 4 Maverick (FP8), Deepinfra: 1m context, Llama 4 Maverick (Turbo, FP8), Deepinfra: 8k context, Llama 4 Maverick (FP8), Novita: 1m context, Llama 4 Maverick (FP8), GMI: 1m context, Llama 4 Maverick, Groq: 131k context, Llama 4 Maverick, SambaNova: 131k context, Llama 4 Maverick, Together.ai: 1m context

Function (Tool) Calling & JSON Mode: Llama 4 Maverick Providers

Models	Function calling	JSON Mode
Lambda (FP8)
Parasail (FP8)
Cerebras
Amazon
Google Vertex
Azure (FP8)
Fireworks (Base)
Deepinfra (FP8)
Deepinfra (Turbo, FP8)
Novita (FP8)
GMI (FP8)
Groq
SambaNova
Together.ai

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.

Llama 4 Maverick: API Provider Benchmarking & Analysis

Llama 4 Maverick: API Provider Benchmarking & Analysis

Highlights

Navigation

Summary Table of Key Comparison Metrics

Summary Analysis

Output Speed vs. Price: Llama 4 Maverick Providers

Latency vs. Output Speed: Llama 4 Maverick Providers

Context Window: Llama 4 Maverick Providers

Pricing

Pricing: Input and Output Prices: Llama 4 Maverick Providers

Speed

Output Speed: Llama 4 Maverick Providers

Output Speed Variance: Llama 4 Maverick Providers

Output Speed by Input Token Count (Context Length): Llama 4 Maverick Providers

Latency

Time to First Token: Llama 4 Maverick Providers

Time to First Token Variance: Llama 4 Maverick Providers

Latency by Input Token Count (Context Length): Llama 4 Maverick Providers

End-to-End Response Time

End-to-End Response Time vs. Price: Llama 4 Maverick Providers

End-to-End Response Time: Llama 4 Maverick Providers

End-to-End Response Time by Input Token Count (Context Length): Llama 4 Maverick Providers

API Features

Function (Tool) Calling & JSON Mode: Llama 4 Maverick Providers