AI Models Catalog | MoonFi.ai - Browse & Compare 50+ Models

37 AI Models

Complete Models Catalog

Browse all available AI models or compare up to 3 side-by-side.

Claude Sonnet 4.5 (Thinking 32k)

Anthropic

reasoning

Context:200K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1448

Speed:85 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude Opus 4.1 (Thinking 16k)

Anthropic

reasoning

Context:200K tokens

Input:$15/1M

Output:$75/1M

LMSYS Rating:1448

Speed:60 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude Sonnet 4.5

Anthropic

text

Context:200K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1436

Speed:85 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude Opus 4.1

Anthropic

reasoning

Context:200K tokens

Input:$15/1M

Output:$75/1M

LMSYS Rating:1439

Speed:60 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude 3.5 Sonnet

Anthropic

coding

Context:200K tokens

Input:$3/1M

Output:$15/1M

Capabilities:

StreamingToolsVisionJSON Mode

Claude 3 Haiku

Anthropic

text

Context:200K tokens

Input:$0.25/1M

Output:$1.25/1M

Capabilities:

StreamingToolsVisionJSON Mode

GPT-4.5 Preview

OpenAI

text

Context:400K tokens

Input:$1.25/1M

Output:$10/1M

LMSYS Rating:1442

Speed:100 t/s

Capabilities:

StreamingToolsVisionJSON Mode

GPT-5 (high)

OpenAI

reasoning

Context:400K tokens

Input:$1.25/1M

Output:$10/1M

LMSYS Rating:1437

Speed:95 t/s

Capabilities:

StreamingToolsVisionJSON Mode

O3

OpenAI

reasoning

Context:128K tokens

Input:$15/1M

Output:$60/1M

LMSYS Rating:1433

Speed:40 t/s

Capabilities:

ToolsJSON Mode

O1

OpenAI

reasoning

Context:128K tokens

Input:$15/1M

Output:$60/1M

Capabilities:

ToolsJSON Mode

ChatGPT-4o Latest

OpenAI

multimodal

Context:128K tokens

Input:$5/1M

Output:$15/1M

LMSYS Rating:1438

Speed:100 t/s

Capabilities:

StreamingToolsVisionJSON Mode

GPT-4o Mini

OpenAI

text

Context:128K tokens

Input:$0.15/1M

Output:$0.6/1M

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 2.5 Pro

Google AI

multimodal

Context:1000K tokens

Input:$2.5/1M

Output:$15/1M

LMSYS Rating:1452

Speed:150 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 2.5 Flash

Google AI

multimodal

Context:1000K tokens

Input:$0.075/1M

Output:$0.3/1M

LMSYS Rating:1270

Speed:200 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 1.5 Pro

Google AI

multimodal

Context:1000K tokens

Input:$1.25/1M

Output:$5/1M

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 1.5 Flash

Google AI

multimodal

Context:1000K tokens

Input:$0.075/1M

Output:$0.3/1M

Capabilities:

StreamingToolsVisionJSON Mode

DeepSeek R1

DeepSeek

reasoning

Context:64K tokens

Input:$0.55/1M

Output:$2.19/1M

LMSYS Rating:1348

Speed:120 t/s

Capabilities:

StreamingToolsJSON Mode

DeepSeek V3

DeepSeek

coding

Context:64K tokens

Input:$0.27/1M

Output:$1.1/1M

Capabilities:

StreamingToolsJSON Mode

DeepSeek V2.5 (FIM)

DeepSeek

coding

Context:64K tokens

Input:$0.27/1M

Output:$1.1/1M

LMSYS Rating:1028

Speed:130 t/s

Capabilities:

StreamingToolsJSON Mode

Grok 4 Fast Search

xAI

text

Context:131K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1166

Speed:110 t/s

Capabilities:

StreamingToolsJSON Mode

Grok 4 Search

xAI

text

Context:131K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1141

Speed:105 t/s

Capabilities:

StreamingToolsJSON Mode

Sonar Pro High

Perplexity AI

text

Context:128K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1149

Speed:90 t/s

Capabilities:

StreamingToolsJSON Mode

Sonar Reasoning Pro High

Perplexity AI

reasoning

Context:128K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1127

Speed:85 t/s

Capabilities:

StreamingToolsJSON Mode

Llama 4 Scout

Meta

text

Context:10000K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Llama 3.1 405B

Meta

reasoning

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Llama 3.1 70B

Meta

coding

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Llama 3.1 8B

Meta

text

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Mistral Large

Mistral AI

reasoning

Context:128K tokens

Input:$2/1M

Output:$6/1M

Capabilities:

StreamingToolsJSON Mode

Mistral Medium

Mistral AI

text

Context:64K tokens

Input:$1/1M

Output:$3/1M

Capabilities:

StreamingToolsJSON Mode

Codestral

Mistral AI

coding

Context:64K tokens

Input:$1/1M

Output:$3/1M

Capabilities:

StreamingToolsJSON Mode

Qwen 3 Max Preview

Alibaba (Qwen)

reasoning

Context:131K tokens

Input:$0.4/1M

Output:$1.2/1M

LMSYS Rating:1433

Speed:100 t/s

Capabilities:

StreamingToolsJSON Mode

Qwen 3

Alibaba (Qwen)

text

Context:131K tokens

Input:$0.4/1M

Output:$1.2/1M

Capabilities:

StreamingToolsJSON Mode

Qwen 2.5 Coder 32B

Alibaba (Qwen)

coding

Context:32K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Command R+

Cohere

text

Context:256K tokens

Input:$2.5/1M

Output:$10/1M

Capabilities:

StreamingToolsJSON Mode

Command R

Cohere

text

Context:128K tokens

Input:$1/1M

Output:$3/1M

Capabilities:

StreamingToolsJSON Mode

Auto (Best for Prompt)

OpenRouter

text

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsVisionJSON Mode

AI SDK (Auto-select)

AI SDK Gateway

text

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsVisionJSON Mode

Loading MEMELinked DEX

Still connecting. This is taking longer than usual. Reload

37 AI Models

Complete Models Catalog

Browse all available AI models or compare up to 3 side-by-side.

Claude Sonnet 4.5 (Thinking 32k)

Anthropic

reasoning

Context:200K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1448

Speed:85 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude Opus 4.1 (Thinking 16k)

Anthropic

reasoning

Context:200K tokens

Input:$15/1M

Output:$75/1M

LMSYS Rating:1448

Speed:60 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude Sonnet 4.5

Anthropic

text

Context:200K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1436

Speed:85 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude Opus 4.1

Anthropic

reasoning

Context:200K tokens

Input:$15/1M

Output:$75/1M

LMSYS Rating:1439

Speed:60 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Claude 3.5 Sonnet

Anthropic

coding

Context:200K tokens

Input:$3/1M

Output:$15/1M

Capabilities:

StreamingToolsVisionJSON Mode

Claude 3 Haiku

Anthropic

text

Context:200K tokens

Input:$0.25/1M

Output:$1.25/1M

Capabilities:

StreamingToolsVisionJSON Mode

GPT-4.5 Preview

OpenAI

text

Context:400K tokens

Input:$1.25/1M

Output:$10/1M

LMSYS Rating:1442

Speed:100 t/s

Capabilities:

StreamingToolsVisionJSON Mode

GPT-5 (high)

OpenAI

reasoning

Context:400K tokens

Input:$1.25/1M

Output:$10/1M

LMSYS Rating:1437

Speed:95 t/s

Capabilities:

StreamingToolsVisionJSON Mode

O3

OpenAI

reasoning

Context:128K tokens

Input:$15/1M

Output:$60/1M

LMSYS Rating:1433

Speed:40 t/s

Capabilities:

ToolsJSON Mode

O1

OpenAI

reasoning

Context:128K tokens

Input:$15/1M

Output:$60/1M

Capabilities:

ToolsJSON Mode

ChatGPT-4o Latest

OpenAI

multimodal

Context:128K tokens

Input:$5/1M

Output:$15/1M

LMSYS Rating:1438

Speed:100 t/s

Capabilities:

StreamingToolsVisionJSON Mode

GPT-4o Mini

OpenAI

text

Context:128K tokens

Input:$0.15/1M

Output:$0.6/1M

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 2.5 Pro

Google AI

multimodal

Context:1000K tokens

Input:$2.5/1M

Output:$15/1M

LMSYS Rating:1452

Speed:150 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 2.5 Flash

Google AI

multimodal

Context:1000K tokens

Input:$0.075/1M

Output:$0.3/1M

LMSYS Rating:1270

Speed:200 t/s

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 1.5 Pro

Google AI

multimodal

Context:1000K tokens

Input:$1.25/1M

Output:$5/1M

Capabilities:

StreamingToolsVisionJSON Mode

Gemini 1.5 Flash

Google AI

multimodal

Context:1000K tokens

Input:$0.075/1M

Output:$0.3/1M

Capabilities:

StreamingToolsVisionJSON Mode

DeepSeek R1

DeepSeek

reasoning

Context:64K tokens

Input:$0.55/1M

Output:$2.19/1M

LMSYS Rating:1348

Speed:120 t/s

Capabilities:

StreamingToolsJSON Mode

DeepSeek V3

DeepSeek

coding

Context:64K tokens

Input:$0.27/1M

Output:$1.1/1M

Capabilities:

StreamingToolsJSON Mode

DeepSeek V2.5 (FIM)

DeepSeek

coding

Context:64K tokens

Input:$0.27/1M

Output:$1.1/1M

LMSYS Rating:1028

Speed:130 t/s

Capabilities:

StreamingToolsJSON Mode

Grok 4 Fast Search

xAI

text

Context:131K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1166

Speed:110 t/s

Capabilities:

StreamingToolsJSON Mode

Grok 4 Search

xAI

text

Context:131K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1141

Speed:105 t/s

Capabilities:

StreamingToolsJSON Mode

Sonar Pro High

Perplexity AI

text

Context:128K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1149

Speed:90 t/s

Capabilities:

StreamingToolsJSON Mode

Sonar Reasoning Pro High

Perplexity AI

reasoning

Context:128K tokens

Input:$3/1M

Output:$15/1M

LMSYS Rating:1127

Speed:85 t/s

Capabilities:

StreamingToolsJSON Mode

Llama 4 Scout

Meta

text

Context:10000K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Llama 3.1 405B

Meta

reasoning

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Llama 3.1 70B

Meta

coding

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Llama 3.1 8B

Meta

text

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Mistral Large

Mistral AI

reasoning

Context:128K tokens

Input:$2/1M

Output:$6/1M

Capabilities:

StreamingToolsJSON Mode

Mistral Medium

Mistral AI

text

Context:64K tokens

Input:$1/1M

Output:$3/1M

Capabilities:

StreamingToolsJSON Mode

Codestral

Mistral AI

coding

Context:64K tokens

Input:$1/1M

Output:$3/1M

Capabilities:

StreamingToolsJSON Mode

Qwen 3 Max Preview

Alibaba (Qwen)

reasoning

Context:131K tokens

Input:$0.4/1M

Output:$1.2/1M

LMSYS Rating:1433

Speed:100 t/s

Capabilities:

StreamingToolsJSON Mode

Qwen 3

Alibaba (Qwen)

text

Context:131K tokens

Input:$0.4/1M

Output:$1.2/1M

Capabilities:

StreamingToolsJSON Mode

Qwen 2.5 Coder 32B

Alibaba (Qwen)

coding

Context:32K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsJSON Mode

Command R+

Cohere

text

Context:256K tokens

Input:$2.5/1M

Output:$10/1M

Capabilities:

StreamingToolsJSON Mode

Command R

Cohere

text

Context:128K tokens

Input:$1/1M

Output:$3/1M

Capabilities:

StreamingToolsJSON Mode

Auto (Best for Prompt)

OpenRouter

text

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsVisionJSON Mode

AI SDK (Auto-select)

AI SDK Gateway

text

Context:128K tokens

Input:$0/1M

Output:$0/1M

Capabilities:

StreamingToolsVisionJSON Mode