Model catalogue

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

Alibaba's latest flagship closed model with vision capabilities, function calling, and Mixture-of-Experts architecture.…

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

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

The latest Opus 4.7 model from Anthropic — notable improvements in software engineering, instruction following, vision …

Claude Opus 4.7 with effort set to max for highest reasoning and creativity, ideal for complex agentic tasks

Anthropic's most capable widely released model, with a 1M token context window, 128k max output, and always-on adaptive…

Claude Opus 4.8 with medium thinking

Claude Opus with Max thinking.

Anthropic's Claude Opus 5 with a 1M token context window, adaptive thinking, and strong deep-reasoning and long-horizon…

Claude Opus 5 with Max thinking effort for the deepest reasoning and long-horizon agentic tasks. 1M token context windo…

Claude Opus 5 with Medium thinking effort for faster, balanced reasoning. 1M token context window.

Anthropic's next-generation Sonnet: the best combination of speed and intelligence, with a 1M token context window, 128…

Claude Sonnet 5 with effort set to max for highest reasoning and creativity, ideal for complex agentic tasks. 1M token …

The latest Opus 4.6 model from Anthropic

The latest Opus 4.6 model from Anthropic with effort set to max for highest reasoning and creativity, ideal for complex…

The latest Sonnet 4.6 model from Anthropic

The latest Sonnet 4.6 model from Anthropic with effort set to max for highest reasoning and creativity, ideal for compl…

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

Latest DeepSeek model hosted in the US.

Official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilitie…

Deep reasoning model from DeepSeek hosted securely in the USA

DeepSeek's August 13 frontier Mixture-of-Experts model for long-context reasoning, coding, and agentic work, served thr…

Gemini 3.1 Pro: Google's most advanced AI model combining breakthrough reasoning depth, native multimodal understanding…

Gemini 3.1 Pro (thinking): Google's most advanced AI model combining breakthrough reasoning depth, native multimodal un…

Gemini 3 Flash: Frontier intelligence built for speed. Pro-grade reasoning at Flash-level latency, 3x faster than 2.5 P…

Gemini 3 Flash with thinking enabled. Thinking level high for deeper reasoning while maintaining Flash-level speed.

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

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

Google's most capable Flash model, built for complex coding, agentic workflows, and reliable multi-step execution. Sign…

Optimized for multi-step orchestration, full-stack code refactoring, and general reasoning. More token-efficient than 3…

Sustained frontier-level intelligence optimized for real-world tasks at higher speed and lower cost. Designed for the a…

Low-latency, cost-effective multimodal model optimized for high-throughput subagent tasks, document parsing and high-vo…

Meta's dense 29B model for autonomous agentic work, multimodal understanding, multi-step reasoning, schema-based tool c…

MiniMax's 428B-parameter Mixture-of-Experts model with 23B active parameters, sparse attention, function calling, and s…

Mistral Large 3, is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Expert…

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

Kimi K3 is Moonshot's most capable flagship model to date, with 2.8 trillion parameters. Built on Kimi Delta Attention …

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long…

Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and n…

GPT-5.6 Luna is optimized for cost-sensitive, high-volume workloads. Features 1.05M context window, 128k output tokens,…

GPT-5.6 Luna configured with high reasoning effort. Optimized for cost-sensitive workloads requiring deeper thinking.

GPT-5.6 Sol is OpenAI's frontier model for the most complex professional work. Features 1.05M context window, 128k outp…

GPT-5.6 Sol configured with high reasoning effort for the most complex professional tasks.

GPT-5.6 Terra balances intelligence and cost. Features 1.05M context window, 128k output tokens, and reasoning token su…

GPT-5.6 Terra configured with high reasoning effort. Balances intelligence and cost for complex tasks.

OpenAI's newest frontier model for the most complex professional work. Features 1.05M context window, 128k output token…

OpenAI's newest frontier model configured with high reasoning effort for the most complex professional tasks.

OpenAI's frontier model for complex professional work. Features 1.05M context window, 128k output tokens, and reasoning…

OpenAI's frontier model configured with high reasoning effort for complex professional tasks.

OpenAI's frontier model configured with high reasoning effort for complex professional tasks.

Our strongest mini model yet for coding, computer use, and subagents. Brings the strengths of GPT-5.4 to a faster, more…

OpenAI's flagship model for coding and agentic tasks across industries. Features 400k context window and multimodal out…

OpenAI's flagship model configured to xhigh reasoning effort.

OpenAI's ChatGPT variation using the latest GPT-5.2 model.

OpenAI's most capable agentic coding model to date, built on GPT-5.3. Optimized for agentic coding tasks including buil…

OpenAI's coding-optimized model built on GPT-5.2. Designed for agentic coding tasks including building projects from sc…

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

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

A version of GPT-5.1 optimized for agentic coding tasks.

A version of GPT-5.1 optimized for coding tasks set in max mode.

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

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

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

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

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

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

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

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

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

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

Automatically routes your message to the best model for the task. Uses AI to detect code, math, creative writing, analy…

GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance pe…

Z.ai's next-generation 754B MoE flagship model built for agentic engineering, with stronger coding capabilities and sus…

xAI's flagship Grok 4.6 model configured with xhigh maximum reasoning for the most complex long-horizon coding and know…

xAI's flagship model built for long-horizon agentic coding and real-world knowledge work. 500K context window.

xAI's intelligent coding model for agentic software, engineering, and workflow tasks. 500K context window.

xAI's flagship enterprise model (1M context). Excels at data extraction, coding, summarization.