AI model directory

Choose from the models that matter.

Compare published models by real constraints—provider, modality, capabilities, limits, and explicit per-token pricing.

32

Labs

139

Providers

76

Model families

Try “claude”, “deepseek”, or “embedding”

Showing 1–12 of 352

Published models

Open multilingual model optimized for generation across 23 languages

Context
128,000
Providers
1
Input / 1M
Unknown
Output / 1M
Unknown
Open weightsText input
Review providers and fit

Compact open multilingual model optimized for generation across 23 languages

Context
8,000
Providers
1
Input / 1M
Unknown
Output / 1M
Unknown
Open weightsText input
Review providers and fit

Open multilingual vision model for OCR, visual reasoning, and image question answering

Context
16,000
Providers
1
Input / 1M
Unknown
Output / 1M
Unknown
Open weightsText inputImage input
Review providers and fit

Compact open multilingual vision model for OCR and visual question answering

Context
16,000
Providers
1
Input / 1M
Unknown
Output / 1M
Unknown
Open weightsText inputImage input
Review providers and fit

Claude model for creative writing, analysis, and controlled agent workflows

Context
1,000,000
Providers
17
Input / 1M
$3
Output / 1M
$18
ReasoningText inputImage inputPdf input
Review providers and fit

Legacy model retained for compatibility with older integrations

Context
200,000
Providers
1
Input / 1M
$0.25
Output / 1M
$1.25
Text inputImage inputPdf input
Review providers and fit

Fast Claude model for responsive assistance, classification, and lightweight agents

Context
200,000
Providers
4
Input / 1M
$0.8
Output / 1M
$4
Text inputImage inputPdf input
Review providers and fit

Fast Claude model for responsive assistance, classification, and lightweight agents

Context
200,000
Providers
14
Input / 1M
$0.14
Output / 1M
$0.71
ReasoningText inputImage inputPdf input
Review providers and fit

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Context
200,000
Providers
25
Input / 1M
$0.85
Output / 1M
$4.3
ReasoningText inputImage inputPdf input
Review providers and fit

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Context
200,000
Providers
7
Input / 1M
$13.5
Output / 1M
$67.5
ReasoningText inputImage inputPdf input
Review providers and fit

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Context
200,000
Providers
0
Input / 1M
Unknown
Output / 1M
Unknown
ReasoningText inputImage inputPdf input
Review providers and fit

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Context
200,000
Providers
10
Input / 1M
$13.5
Output / 1M
$67.5
ReasoningText inputImage inputPdf input
Review providers and fit