document-understanding

Available in 6 models across 2 providers

Providers

Google
Anthropic

Models with this Capability

gemini-2.5-pro-preview-05-06

Google · Gemini 2.5

preview

Input

1.0M tokens

Output

65.5K tokens

Input Cost

$1.25/1M

Output Cost

$10.00/1M

Exceptional at:

Complex reasoning
Multimodal
+1
Multimodal input
Long context
Function calling
+6

claude-3-7-sonnet-20250219

Anthropic · Claude 3.7

GA

Input

200K tokens

Output

64K tokens

Input Cost

$3.00/1M

Output Cost

$15.00/1M

Exceptional at:

Complex reasoning
Multimodal
+1
Multimodal input
Long context
Extended thinking
+3

claude-3-5-sonnet-20241022

Anthropic · Claude 3.5

GA

Input

200K tokens

Output

8.2K tokens

Input Cost

$3.00/1M

Output Cost

$15.00/1M

Exceptional at:

Complex reasoning
Multimodal
Multimodal input
Long context
Advanced reasoning
+2

claude-3-5-haiku-20241022

Anthropic · Claude 3.5

GA

Input

200K tokens

Output

8.2K tokens

Input Cost

$0.80/1M

Output Cost

$4.00/1M

Exceptional at:

Fast
Affordable
Multimodal input
Long context
Code generation
+1

claude-3-opus-20240229

Anthropic · Claude 3

GA

Input

200K tokens

Output

4.1K tokens

Input Cost

$15.00/1M

Output Cost

$75.00/1M

Exceptional at:

Complex reasoning
Multimodal
Multimodal input
Long context
Advanced reasoning
+2

claude-3-haiku-20240307

Anthropic · Claude 3

GA

Input

200K tokens

Output

4.1K tokens

Input Cost

$0.25/1M

Output Cost

$1.25/1M

Exceptional at:

Fast
Affordable
Multimodal input
Long context
Code generation
+1

Similar Capabilities