AI Model Encyclopedia

100 models across 8 providers — real pricing, context windows, and what each is best for.

Anthropic

17 models

Claude 3 Haiku

👁🔧

Anthropics fastest and most compact model. Ideal for near-instant responsiveness and high-volume tasks where cost matters.

200K ctx$0.25/M in$1.25/M out

Claude 3 Opus

👁🔧

Anthropics most powerful Claude 3 model. Excels at complex analysis, research, and nuanced understanding. Superseded by Claude 3.5 models.

200K ctx$15/M in$75/M out

Claude 3 Sonnet

👁🔧

Balanced performance and speed from the Claude 3 generation. Superseded by Claude 3.5 Sonnet but still available.

200K ctx$3/M in$15/M out

Claude 3.5 Haiku

🔧

The fastest Claude 3.5 model. Matches Claude 3 Opus intelligence at a fraction of the cost, with near-instant response times.

200K ctx$0.8/M in$4/M out

Claude 3.5 Sonnet

👁🔧

Anthropics flagship model. Outperforms Claude 3 Opus at twice the speed and a fraction of the cost. Exceptional at coding, writing, and analysis.

200K ctx$3/M in$15/M out

Claude 3.7 Sonnet

👁🔧

Anthropics most intelligent model to date. Features extended thinking mode for complex multi-step reasoning and hard problems.

200K ctx$3/M in$15/M out

Claude Haiku 4

👁🔧

Fastest, most cost-efficient model

200K ctx$1/M in$5/M out

Claude Haiku 4.5

🔧

Fast, lightweight tasks and high-throughput applications

200K ctx$0.8/M in$4/M out

Claude Opus 4

👁🔧

Most intelligent model for agents and coding

200K ctx$15/M in$75/M out

Claude Opus 4.1

👁🔧

Most capable tasks — complex reasoning, research, and long-form writing

200K ctx$15/M in$75/M out

Claude Opus 4.5

👁🔧

Legacy high-intelligence model

200K ctx$5/M in$25/M out

Claude Opus 4.6

👁🔧

Most capable tasks — complex reasoning, research, and long-form writing

200K ctx$15/M in$75/M out

Claude Opus 4.7

👁🔧

Anthropic's most powerful model, excelling at complex reasoning, nuanced analysis, and demanding tasks that require depth and precision.

200K ctx$15/M in$75/M out

Claude Opus 4.8

👁🔧

Most capable tasks — complex reasoning, research, and long-form writing

Claude Sonnet 4

👁🔧

Optimal balance of intelligence, cost, and speed

200K ctx$3/M in$15/M out

Claude Sonnet 4.5

👁🔧

Legacy model with balanced performance

200K ctx$3/M in$15/M out

Claude Sonnet 4.6

👁🔧

Balanced performance and speed for production applications

200K ctx$3/M in$15/M out

DeepSeek

2 models

Google

20 models

Gemini 1.5 Flash

👁🔧

Googles fast, efficient multimodal model with a massive 1M token context window. Excellent price-to-performance for most tasks.

1000K ctx$0.075/M in$0.3/M out

Gemini 1.5 Pro

👁🔧

Googles most capable Gemini 1.5 model with a 2M token context window — the largest of any commercially available model. Excellent for long documents and video.

2000K ctx$1.25/M in$5/M out

Gemini 2.0 Flash

👁🔧

Next-generation fast model from Google. Improved performance over 1.5 Flash with added agentic capabilities and real-time information access.

1000K ctx$0.1/M in$0.4/M out

Gemini 2.0 Flash-Lite

👁🔧

Gemini 2.0 Flash-Lite

1049K ctx$0.075/M in$0.3/M out

Gemini 2.0 Pro

👁🔧

Googles most capable Gemini 2.0 model. Strongest coding and world knowledge of the Gemini family. Designed for complex agentic tasks.

1000K ctx$0/M in$0/M out

Gemini 2.5 Flash

👁🔧

Low-latency, high-volume tasks that require reasoning with best price-performance.

1049K ctx$0.3/M in$2.5/M out

Gemini 2.5 Flash-Lite

👁🔧

The fastest and most budget-friendly multimodal model in the 2.5 family.

1049K ctx$0.1/M in$0.4/M out

Gemini 2.5 Pro

👁🔧

Complex tasks featuring deep reasoning and coding capabilities.

1049K ctx$1.25/M in$10/M out

Gemini 2.5 Pro Flash

👁🔧

Efficient processing of multimodal content with fast inference.

1049K ctx$1.25/M in$10/M out

Gemini 3 Flash

👁🔧

Frontier-class performance rivaling larger models at a fraction of the cost.

1049K ctx$0.3/M in$2.5/M out

Gemini 3 Pro

👁🔧

Complex multimodal tasks and advanced reasoning

1049K ctx

Gemini 3.1 Flash

👁🔧

Fast multimodal processing with image generation capabilities

1049K ctx$0.3/M in$2.5/M out

Gemini 3.1 Pro

👁🔧

Advanced intelligence, complex problem-solving, and powerful agentic and vibe coding capabilities.

1049K ctx$2/M in$12/M out

Gemini 3.5 Flash

👁🔧

Most intelligent model for sustained frontier performance on agentic and coding tasks.

1049K ctx$1.5/M in$9/M out

Gemini Deep Research

🔧

Autonomous multi-step research across hundreds of sources to produce cited, interactive reports.

1000K ctx$3.5/M in$10.5/M out

Gemini Deep Research Max

🔧

Maximum comprehensiveness for automated context gathering and synthesis across hundreds of sources.

1000K ctx$5/M in$15/M out

Gemini Robotics-ER 1.6

👁🔧

Advanced embodied reasoning model for robotic agents with spatial and physical reasoning.

Imagen 4

High-quality image generation and editing

Lyria 3

High-quality music generation from text prompts

Veo 3.1

Advanced video generation from text and image prompts

Meta

18 models

Llama 3.1

🔧

Text summarization, multilingual agents, and coding use cases with tool use capabilities.

Llama 3.1 405B

🔧

Metas largest and most capable open-source model. Competes directly with GPT-4o and Claude 3.5 Sonnet on many benchmarks — and its free.

128K ctx$0.9/M in$0.9/M out

Llama 3.1 405B

🔧

Text summarization, multilingual agents, and coding use cases with maximum capability.

Llama 3.1 70B

🔧

Text summarization, multilingual agents, and coding use cases.

Llama 3.1 70B

🔧

Metas mid-size open-source model. Competitive with many commercial models at zero licensing cost. Requires significant hardware to self-host.

128K ctx$0.34/M in$0.39/M out

Llama 3.1 8B

🔧

Metas smallest open-source Llama 3.1 model. Free to download and run locally. Surprisingly capable for its size, especially for on-device use.

128K ctx$0.02/M in$0.05/M out

Llama 3.1 8B

🔧

Text summarization, multilingual agents, and coding use cases.

Llama 3.2

👁

Cost-effective edge deployment with multimodal capabilities for image reasoning.

Llama 3.2 11B

👁

Flexible multimodal reasoning on high-resolution images with text output.

Llama 3.2 11B Vision

👁

Metas first open-source multimodal Llama model. Understands images and text together. Ideal for vision tasks without cloud dependency.

128K ctx$0.05/M in$0.05/M out

Llama 3.2 1B

Lightweight, cost-efficient edge deployment for text-based applications.

Llama 3.2 3B

Lightweight, cost-efficient edge deployment for text-based applications.

Llama 3.2 90B

👁

Flexible multimodal reasoning on high-resolution images with text output.

Llama 3.3

Multilingual text-based use cases such as synthetic data generation.

Llama 3.3 70B

Text-based use cases such as synthetic data generation with 405B-level performance.

Llama 3.3 70B

Metas latest 70B model with improved instruction following and reasoning. Delivers 405B-level performance in a more efficient package.

128K ctx$0.1/M in$0.32/M out

Llama 4 Maverick

👁

Long-form multimodal work with native image and text understanding.

10000K ctx$0.19/M in$0.49/M out

Llama 4 Scout

👁

Long document analysis with efficient single GPU deployment.

10000K ctx$0.19/M in$0.49/M out

Microsoft

8 models

OpenAI

27 models

GPT-3.5-TURBO

🔧

General-purpose language tasks

16K ctx$0.5/M in$1.5/M out

GPT-4

🔧

General-purpose language tasks

8K ctx$30/M in$60/M out

GPT-4 Turbo

👁🔧

Previous generation flagship from OpenAI. Largely superseded by GPT-4o but still available. Solid performance on complex reasoning tasks.

128K ctx$10/M in$30/M out

GPT-4.1

👁🔧

Instruction-following and agentic coding workflows

1048K ctx$2/M in$8/M out

GPT-4.1 mini

👁🔧

Instruction-following and agentic coding workflows

1048K ctx$0.4/M in$1.6/M out

GPT-4.1 nano

👁🔧

Instruction-following and agentic coding workflows

1048K ctx$0.1/M in$0.4/M out

GPT-4o

👁🔧

OpenAIs flagship multimodal model. Fast, highly capable across text, vision, and audio. The most widely used frontier model.

128K ctx$2.5/M in$10/M out

GPT-4o mini

👁🔧

A smaller, cheaper version of GPT-4o. Surprisingly capable for its price point. Ideal for high-volume, cost-sensitive applications.

128K ctx$0.15/M in$0.6/M out

GPT-5

🔧

General-purpose language tasks

400K ctx$1.25/M in$10/M out

GPT-5-MINI

🔧

General-purpose language tasks

400K ctx$0.25/M in$2/M out

GPT-5-NANO

🔧

General-purpose language tasks

400K ctx$0.05/M in$0.4/M out

GPT-5-PRO

🔧

General-purpose language tasks

400K ctx$15/M in$120/M out

GPT-5.1

🔧

General-purpose language tasks

400K ctx$1.25/M in$10/M out

GPT-5.2

🔧

General-purpose language tasks

400K ctx$1.75/M in$14/M out

GPT-5.2-PRO

🔧

General-purpose language tasks

400K ctx$21/M in$168/M out

GPT-5.4

🔧

General-purpose language tasks

1050K ctx$2.5/M in$15/M out

GPT-5.4-MINI

🔧

General-purpose language tasks

400K ctx$0.75/M in$4.5/M out

GPT-5.4-NANO

🔧

General-purpose language tasks

400K ctx$0.2/M in$1.25/M out

GPT-5.4-PRO

🔧

General-purpose language tasks

1050K ctx$30/M in$180/M out

GPT-5.5

🔧

General-purpose language tasks

1050K ctx$5/M in$30/M out

GPT-5.5-PRO

🔧

General-purpose language tasks

1050K ctx$30/M in$180/M out

GPT-IMAGE-1

🔧

General-purpose language tasks

$5/M in$15/M out

o1

🔧

OpenAIs first reasoning model. Thinks before answering using chain-of-thought internally. Excels at math, science, and complex coding problems.

200K ctx$15/M in$60/M out

o1 Pro

🔧

Deep reasoning tasks requiring careful step-by-step thinking

200K ctx$150/M in$600/M out

o3

👁🔧

Advanced reasoning and complex problem-solving

200K ctx$2/M in$8/M out

o3 mini

👁🔧

Advanced reasoning and complex problem-solving

200K ctx$1.1/M in$4.4/M out

o4 mini

👁🔧

Advanced reasoning and complex problem-solving

200K ctx$1.1/M in$4.4/M out

Perplexity

2 models

xAI

6 models