Summary Analysis

Visual Reasoning vs. Image Input Price

Visual reasoning intelligence: MMMU Pro evaluation · Image input price: USD per 1k images at 1MP (1024x1024)

Most attractive quadrant

Based on the MMMU Pro evaluation of 1.7k questions, this represents the model's ability to interpret and reason over images.

Price for 1,000 images at a resolution of 1 Megapixel (1024 x 1024) processed by the model.

Visual Reasoning vs. Latency (Single Image & 1,000 Language Tokens Input)

Visual reasoning intelligence: MMMU Pro evaluation · Seconds to first token received

Most attractive quadrant

Based on the MMMU Pro evaluation of 1.7k questions, this represents the model's ability to interpret and reason over images.

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.

Intelligence

Visual Reasoning Intelligence (MMMU Pro evaluation)

Visual reasoning intelligence: MMMU Pro evaluation

Multimodal reasoning quality evaluation based on 1.7k questions which require interpreting and reasoning over images.

Pricing

Pricing: Image Input Pricing

Image input price: USD per 1k images at 1MP (1024x1024)

Price for 1,000 images at a resolution of 1 Megapixel (1024 x 1024) processed by the model.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Pricing: Language Input, Image Input and Language Output

Price (USD per M Tokens) · Image input price: USD per 1k images at 1MP (1024x1024) · Lower is better

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

Latency & Speed

Latency (Single Image & 1,000 Language Tokens Input)

Seconds to first token received · Lower is better

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 performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latency Variance (Single Image & 1,000 Language Tokens Input)

Seconds to first token received · Results by percentile · Lower is better

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.

Output Speed (Single Image & 1,000 Language Tokens Input)

Output tokens per second · Higher is better

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 performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Vision Models: LLMs with Image Input Capabilities

Intelligence

Speed

Price

Summary Analysis

Visual Reasoning vs. Image Input Price

Visual Reasoning

Price per 1k 1MP Images

Visual Reasoning vs. Latency (Single Image & 1,000 Language Tokens Input)

Visual Reasoning

Latency (Time to First Token)

Intelligence

Visual Reasoning Intelligence (MMMU Pro evaluation)

MMMU Pro

Pricing

Pricing: Image Input Pricing

Price per 1k 1MP Images

Model Performance Representation

Pricing: Language Input, Image Input and Language Output

Input Price

Latency & Speed

Latency (Single Image & 1,000 Language Tokens Input)

Latency (Time to First Token)

Model Performance Representation

Latency Variance (Single Image & 1,000 Language Tokens Input)

Latency (Time to First Token)

Boxplot

Output Speed (Single Image & 1,000 Language Tokens Input)

Output Speed

Model Performance Representation