Model catalogue

Qwen3 30b A3B

Latest Qwen3 state of the art model, 30B-A3B version

Context: 32,768 Output: 8,000

Amazon Nova Pro Vision

Amazon's pro multi-modal model that can process text, images, and videos to generate text

Context: 32,000 Output: 2,048

Amazon Nova Lite Vision

Amazon's lite multi-modal model that can process text, images, and videos to generate text

Context: 32,000 Output: 2,048

Claude 4.5 Sonnet Frontier Vision

The latest Claude 4.5 Sonnet model from Anthropic with a 1M token context window.

Context: 1,000,000 Output: 64,000

Claude 4.5 Sonnet (thinking) Frontier Vision

The latest Claude 4.5 Sonnet model from Anthropic with maximum reasoning enabled, 200k reasoning tokens in 1M context.

Context: 1,000,000 Output: 64,000

Claude 4.1 Opus Frontier Vision

The latest Opus 4.1 model from Anthropic

Context: 200,000 Output: 64,000

Claude 4 Opus Frontier Vision

The latest Opus 4 model from Anthropic

Context: 200,000 Output: 64,000

Claude 4.5 Haiku Vision

The latest Claude 4.5 Haiku model from Anthropic with a 1M token context window.

Context: 200,000 Output: 64,000

Claude 4 Opus (thinking) Frontier Vision

The latest Opus 4 model from Anthropic with high thinking mode

Context: 200,000 Output: 64,000

Claude 4 Sonnet Frontier Vision

The latest Sonnet 4 model from Anthropic

Context: 200,000 Output: 64,000

Claude 4 Sonnet (thinking) Frontier Vision

The latest Sonnet 4 model from Anthropic with high thinking mode

Context: 200,000 Output: 64,000

Claude 3.7 Sonnet Frontier Vision

The latest Sonnet 3.7 model from Anthropic

Context: 128,000 Output: 64,000

Claude 3.7 Sonnet (high output) Frontier Vision

The latest Sonnet 3.7 model from Anthropic

Context: 204,800 Output: 128,000

Claude 3.7 Sonnet (thinking) Frontier Vision

The latest Sonnet 3.7 model from Anthropic

Context: 204,800 Output: 64,000

Claude 3.5 Haiku

The latest Haiku 3.5 model from Anthropic

Context: 204,800 Output: 4,096

DeepSeek V3.1 Terminus

A large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. USA ho…

Context: 163,840 Output: 32,000

DeepSeek V3.2 Exp

An experimental model hosted in the US introducing DeepSeek Sparse Attention for training and inference efficiency in l…

Context: 163,840 Output: 32,000

DeepSeek V3.1

DeepSeek's updated V3.1 model releasedhosted securely in the USA

Context: 160,000 Output: 30,000

DeepSeek V3 0324

DeepSeek's updated V3 model released on 03/24/2025 hosted securely in the USA

Context: 131,072 Output: 30,000

DeepSeek-R1 (05/28)

Deep reasoning model from DeepSeek hosted securely in the USA, updated on 05/28/2025

Context: 131,072 Output: 8,192

DeepSeek-R1 (Groq)

The deep reasoning DeepSeek-R1 running on Groq

Context: 131,072 Output: 8,192

Gemini 2.5 Pro Frontier Vision

A powerful reasoning model for problem-solving tasks and multimodal capabilities.

Context: 1,048,756 Output: 65,535

Gemini 2.5 Flash Vision

Multimodal model that is fast, token efficient and performant for complex tasks. 1M context window.

Context: 1,048,576 Output: 64,000

Gemini 2.5 Flash Preview Vision

Preview of Gemini 2.5 Flash always updated to latest. A multimodal model that is fast, token efficient and performant f…

Context: 1,048,576 Output: 64,000

Gemini 2.5 Flash Lite Preview Vision

Google's small fast model preview tied to latest version. Features reduced latency and memory requirements while mainta…

Context: 1,048,576 Output: 8,192

Gemini 2.0 Flash Experimental Vision

An experimental model which supports text and image output. Optimized for creative generation with balanced performance…

Context: 1,048,576 Output: 8,192

Meta Llama 4 Scout

Llama 4 Scout is a versatile small model served with 1M token context suitable for a wide range of applications includi…

Context: 1,000,000 Output: 16,384

Meta Llama 4 Maverick

Llama 4 Maverick is a powerful medium model with 1M token context designed for advanced reasoning tasks and multimodal …

Context: 1,000,000 Output: 16,384

Mistral Medium 3

Mistral Medium 3 is designed to be frontier-class, particularly in categories of professional use.

Context: 128,000 Output: 16,384

Kimi K2

Kimi K2 (0905) is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1…

Context: 256,000 Output: 16,384

GPT-5 Frontier Vision

OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.

Context: 272,000 Output: 128,000

GPT-5 thinking Frontier Vision

OpenAI's flagship model configured for longer thinking.

Context: 272,000 Output: 128,000

GPT-5 mini Vision

A faster, more cost-efficient version of GPT-5 for well-defined tasks and precise prompts.

Context: 272,000 Output: 128,000

GPT-5 nano Vision

The fastest, most cost-efficient version of GPT-5, great for summarization and classification tasks.

Context: 272,000 Output: 128,000

GPT-5 Codex Frontier Vision

OpenAI's specialist coding model.

Context: 400,000 Output: 128,000

GPT-4.1 Frontier Vision

OpenAI's latest model with enhanced capabilities across text, vision and audio

Context: 104,757 Output: 32,768

GPT-4.1-mini Vision

OpenAI's latest model with enhanced capabilities across text, vision and audio

Context: 104,757 Output: 32,768

o4-mini Frontier Vision

The latest o-series model. Optimized for fast & effective reasoning. Best for coding and visual tasks.

Context: 200,000 Output: 100,000

o4-mini-high Frontier Vision

High mode thinks for longer. Optimized for fast & effective reasoning. Best for coding and visual tasks.

Context: 200,000 Output: 100,000

GPT-4o Frontier Vision

The Omni model from OpenAI that reasons across audio vision and text

Context: 128,000 Output: 4,096

GPT-4o mini Vision

OpenAI's affordable and intelligent small model for fast lightweight tasks

Context: 128,000 Output: 16,384

o3-mini Frontier

o3-mini is a fast cost-efficient reasoning model tailored to coding math and science use cases

Context: 200,000 Output: 100,000

o3-mini-high Frontier

o3-mini-high is the higest reasoning level of OpenAI's fast cost-efficient reasoning model tailored to coding math and …

Context: 200,000 Output: 100,000

o1 Frontier

o1 is OpenAI's new reasoning model for complex tasks that require broad general knowledge

Context: 128,000 Output: 100,000

o3 Frontier Vision

o3 is powerful across all domains. It excels at Math, Science, Coding and Visual Reasoning tasks. Best for multi-step p…

Context: 200,000 Output: 100,000

o3-pro Frontier

o3-pro a version of o3 that uses more compute to think harder and provide reliable answers to challenging problems.

Context: 200,000 Output: 100,000

gpt-oss-120b

OpenAI's open-weight model for powerful reasoning and agentic tasks.

Context: 128,000 Output: 16,384

gpt-oss-20b

OpenAI's smaller open-weight model for powerful reasoning and agentic tasks.

Context: 128,000 Output: 16,384

GLM-4.6 Frontier

Advanced model from Zhipu AI with a 200K context window, superior coding, and advanced reasoning capabilities, hosted i…

Context: 200,000 Output: 16,384

GLM-4.5

Foundation model (355B parameters) designed for intelligent agents, unifying reasoning, coding, and agent capabilities.

Context: 128,000 Output: 16,384

Grok 4 Frontier Vision

xAI's flagship enterprise model (256k context). Excels at data extraction, coding, summarization.

Context: 256,000 Output: 8,000

Grok 4 Fast Frontier

Faster Grok 4 with identical quality (2m context). Low latency for time-sensitive tasks and huge context window.

Context: 2,000,000 Output: 30,000

Grok 4 Fast (reasoning) Frontier

Reasoning-enabled Grok 4 with 2m context. Low latency for time-sensitive tasks and huge context window.

Context: 2,000,000 Output: 30,000

Claude 4.5 Sonnet

VS

Claude 4.5 Sonnet (thinking)

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 4.1 Opus

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 4 Opus

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 4 Opus (thinking)

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 4 Sonnet

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 4 Sonnet (thinking)

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 3.7 Sonnet

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 3.7 Sonnet (high output)

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

Claude 3.7 Sonnet (thinking)

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

GPT-5

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

GPT-5 thinking

Compare capabilities, context size, and performance between these models.

View detailed comparison →

Claude 4.5 Sonnet

VS

GPT-5 Codex

Compare capabilities, context size, and performance between these models.

View detailed comparison →