Function calling for agents, MCP servers, and anything that needs the model to hand work back to your code.
DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Mistral Uncensored 1.2 is an uncensored 24B fine-tune of Mistral Small 24B, built on Dolphin Mistral 24B, made for open-ended dialogue, roleplay and creative writing with minimal content restrictions. It accepts text and image input, supports function calling and structured output, and has a 128K-token context window.
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
GLM 5.3 Uncensored is an uncensored variant of Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context window, always reasons at low, high or max depth, and is aimed at red teaming, security research and agent testing.
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.
Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.
MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of up to 1M tokens, and can also operate a desktop computer.
Claude Fable 5 is Anthropic's Mythos-class model released for general use, built for demanding reasoning and long-horizon agentic work. It takes text and image input and produces text output, with a 1M-token context window, up to 128K output tokens and always-on adaptive thinking.
Qwen 3.6 Plus Uncensored is an uncensored variant of Qwen3.6 Plus, the vision-language Plus model from Alibaba's Qwen team. The base model accepts text, image and video input with a 1M-token context window and supports switchable thinking and function calling.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.
GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.
Grok 4.20 is xAI's reasoning model built for speed and agentic tool calling, with low hallucination rates and strict prompt adherence. It takes text and image input and produces text output, with a 1M-token context window, function calling and structured outputs.
GPT-6 Astra is the top tier of OpenAI's GPT-6 family, built for demanding work such as complex reasoning, coding, computer use, research and document creation. It takes text and image input and produces text, with a 1.05M-token context window (up to 922K input and 128K output tokens) and configurable reasoning effort.
GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.
GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier.
GPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.
GPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.
Kolibri 1 is a text model.
DeepSeek V4 Flash (Preview) is the April 2026 preview release of DeepSeek's efficiency-focused Mixture-of-Experts model, with 284B total and 13B active parameters and a 1M-token context window. It offers a non-thinking mode and two thinking levels (high and max) for fast reasoning and coding workloads.
DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled).
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
DeepSeek V4.1 Flash Fast is a lower-latency serving tier of DeepSeek V4.1 Flash, the same model served for faster output. It is a Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window, with strong reasoning, coding, and agentic performance.
Gemini 2.5 Flash-Lite is Google's cost-efficient multimodal model in the Gemini 2.5 family, built for high-frequency, lightweight tasks such as high-volume classification and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and thinking support.
Muse Spark 1.1 is a multimodal reasoning model from Meta Superintelligence Labs, built for agentic tasks. It accepts text, image, video, audio and PDF input, returns text, and has a 1,048,576-token context window that it can actively manage and compact. It is trained for tool use that generalizes to new tools and MCP servers, computer use across multiple applications, coding on large codebases, and orchestrating parallel subagents.
Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 from Meta, co-trained with Meta's Muse Code terminal coding agent. It is a reasoning model with adjustable thinking effort that accepts text, image, video, audio and PDF input, returns text, and has a 1,048,576-token context window. It targets code generation, complex debugging, codebase understanding and long-horizon developer workflows, using planning, goal conditioning, context compaction and parallel tool calls.
Muse Spark 1.3 is a reasoning model from Meta and an update to Muse Spark 1.2, with improved performance on agentic and coding tasks. It accepts text, image, video and PDF input and returns text, with a 1,048,576-token context window and adjustable reasoning effort. It is trained for longer-horizon work, follows long instructions more reliably, asks clarifying questions, confirms consequential actions, and is more resistant to prompt injection.
Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.
Muse Wonder is a reasoning model from Meta Superintelligence Labs for long-running personal and professional agentic work, released in October 2026 as a larger class of model than the Muse Spark family. It accepts text, images, audio, video and PDF documents and returns text, with a context window of about 1M tokens. It is built to plan, call tools in parallel, keep track of what matters across a long task and try another approach when it hits a blocker.
Hy4 Preview is a 770B-parameter Mixture-of-Experts model from the Tencent Hy Team, with 49B parameters active per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with IndexCache and is post-trained for software engineering, office and data analysis, game development and scientific research, with adjustable reasoning effort.
Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software engineering, office and data analysis, game development, and scientific research, with strong long-horizon reasoning, tool use, and agentic performance.
MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agents and cybersecurity tasks.
GLM-5.2 is Z.ai's open-weight Mixture-of-Experts model for long-horizon tasks and software engineering. It takes text input and output with a 1M-token context window and up to 128K output tokens, and offers multiple thinking effort levels to balance performance and latency.
GLM-5.2 Fast is a lower-latency serving tier of GLM-5.2, Z.ai's model for long-horizon tasks, served for faster output. It takes text input and output with a 1M-token context window, and offers stronger coding than GLM-5.1 with multiple thinking effort levels to balance performance and latency.
GLM-5.3 Fast is a lower-latency serving tier of GLM-5.3, Z.ai's reasoning model for complex software engineering and long-horizon agent tasks. It shares GLM-5.2's base model with improved post-training for coding, and supports text input and output with a 1M-token context window.
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
GLM 5.3 Flash Uncensored is a text model.
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.
Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.
Claude Opus 4.6 is Anthropic's Opus model for demanding coding, long-running agentic work and knowledge work such as research, financial analysis and building documents. It takes text and image input and produces text output, with a 1M-token context window, up to 128K output tokens and adaptive thinking with effort controls.
Claude Opus 4.7 is Anthropic's Opus model for advanced software engineering, especially complex, long-running coding tasks. It builds on Opus 4.6 with more precise instruction following, verification of its own outputs and higher-resolution vision, and offers a 1M-token context window, up to 128K output tokens and adaptive thinking.
Claude Opus 4.8 is Anthropic's Opus model for dependable, long-running agentic work and coding. It builds on Opus 4.7 with sharper judgment and more candid flagging of doubts about its own output, and takes text and image input with a 1M-token context window, up to 128K output tokens and adaptive thinking.
Claude Opus 4.8 Fast is Claude Opus 4.8 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text and image input, text output, a 1M-token context window and adaptive thinking for agentic work and complex coding.
Claude Opus 5 is Anthropic's Opus model for daily professional work, with gains over Opus 4.8 in software engineering, knowledge work and scientific research. It checks its own work and iterates until a task succeeds, and takes text and image input with a 1M-token context window, up to 128K output tokens and adaptive thinking.
Claude Opus 5 Fast is Claude Opus 5 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text and image input, text output, a 1M-token context window and adaptive thinking for coding, knowledge work and research.
Claude Opus 5.5 is Anthropic's Opus model for long-running agentic coding and knowledge work. Compared with Opus 5 it uses fewer tokens per task and writes more clearly, and it takes text and image input with a 1M-token context window, up to 128K output tokens and always-on adaptive thinking.
Claude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling.
Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.
Claude Sonnet 5 is Anthropic's Sonnet model built for agentic work: planning, using tools such as browsers and terminals, coding, reasoning and knowledge work. It takes text and image input and produces text, with a 1M-token context window, up to 128K output tokens and adaptive thinking, and improves on Sonnet 4.6.
Claude Sonnet 5.5 is Anthropic's Sonnet model, balancing speed and intelligence for well-scoped everyday work such as building features, fixing bugs and creating documents, slides and spreadsheets. It improves on Sonnet 5 in coding, token efficiency and clear writing, with a 1M-token context window, up to 128K output tokens and adaptive thinking.
DeepSeek V4 Flash 0731 Fast is a faster serving variant of DeepSeek V4 Flash 0731, DeepSeek's July 2026 release of its 284B-parameter Mixture-of-Experts model with 13B active parameters. The model has a 1M-token context window and is re-post-trained for stronger agentic performance, with low, high and max reasoning effort.
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
Gemini 2.5 Flash is Google's thinking model built for price-performance, suited to large-scale processing, low-latency, high-volume tasks and agentic use cases. It takes text, image, video and audio input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.1 Flash-Lite is Google's low-latency, cost-effective multimodal model for high-frequency, lightweight tasks such as high-volume agentic workflows and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window, up to 65K output tokens and thinking support.
Gemini 3.1 Pro Preview is the preview release of Google's Gemini 3.1 Pro, a reasoning model for software engineering and agentic workflows that need precise tool use. It refines the Gemini 3 Pro series with better thinking, improved token efficiency and more grounded, factually consistent answers. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.5 Flash is a Flash model in Google's Gemini 3 series, optimized for real-world tasks at higher speed and lower cost. It supports thinking. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks.
Gemini 3.6 Flash is a Flash model in Google's Gemini 3 series designed for agentic work, with strengths in code generation, agentic execution and spatial reasoning. It suits fast agentic loops with complex coding cycles. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.7 Flash is a Flash model in Google's Gemini 3 series of natively multimodal reasoning models, built as a workhorse for coding and agentic work. It improves on Gemini 3.6 Flash in coding and web development, supports low, medium and high thinking levels, and has a 1M-token context window with up to 65K output tokens.
Gemini 3.8 Flash is a Flash model in Google's Gemini 3 series, engineered for long-horizon software engineering, autonomous agents and complex enterprise workflows at Flash-level speed and cost. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window, up to 65K output tokens and low, medium and high thinking levels.
Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.
Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output support.
MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default).
Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.
Kimi K3.1 Pro is Moonshot AI's flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic workflows, financial research, and 3D modeling through CAD code.
Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI's flagship multimodal reasoning model. It offers the same quality and 1M-token context window with substantially higher output speed for latency-sensitive coding and agentic workflows.
GPT-4.1 is OpenAI's non-reasoning model that excels at instruction following and tool calling, with broad knowledge across domains. It takes text and image input and produces text output, with a 1M-token context window, up to 32K output tokens and low latency without a reasoning step.
GPT-4.1 Mini is a smaller, faster version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces text output, with a 1M-token context window and up to 32K output tokens.
GPT-5.4 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to xhigh.
GPT-5.4 Pro is a version of OpenAI's GPT-5.4 that uses more compute to think harder and give more precise answers on complex, high-stakes tasks. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and medium to xhigh reasoning effort.
GPT-5.5 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to xhigh.
GPT-5.5 Pro is a version of OpenAI's GPT-5.5 that uses more compute to think harder and give more precise answers on complex tasks. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and medium to xhigh reasoning effort.
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 family, built for complex professional work such as reasoning, coding and agentic workflows. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to max.
GPT-5.6 Sol Pro is GPT-5.6 Sol run in OpenAI's pro reasoning mode, which performs more model work per request for difficult tasks that justify higher latency and token use. It is the same underlying model, with text and image input, text output and a context window of about 1.05M tokens.
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced.
GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.
Qwen 3.7 Plus is a multimodal agent model from Alibaba's Qwen team, built on the Qwen3.7 text model and able to operate graphical interfaces and the command line. It accepts text, image and video input with a 1M-token context window and supports switchable thinking and function calling.
Qwen 3.8 27B is an open-weight dense model from Alibaba's Qwen team with 27B parameters and a vision encoder, using hybrid Gated DeltaNet and gated attention layers. It takes text, image and video input with a native 262K-token context window and is built for coding, professional and research work, and long-horizon agentic tasks, with adjustable thinking effort.
Qwen 3.8 Flash is an efficient multimodal model from Alibaba's Qwen team, built on the open-weight Qwen3.8 Flash Next Mixture-of-Experts model with 125B total and 6B active parameters. It accepts text, image and video input with a 1M-token context window, supports function calling and structured output, and has a thinking mode that can be turned off.
Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.
Qwen3.8-Omni-Flash is an omni-modal model from Alibaba's Qwen team, built around agentic audio and video understanding. It takes text, image, audio and video input and produces text output, with a 1M-token context window, thinking enabled by default with adjustable effort, and tool calling. It is built to plan and complete tasks from audio-visual content, such as video editing, film commentary, meeting minutes and audio-visual summarization, and accepts audio in 113 languages and dialects.
Grok 4.3 is xAI's fast, reliable model with strong tool calling and instruction following, suited to agentic workflows. It takes text and image input and produces text output, with a 1M-token context window, function calling, structured outputs and reasoning effort from none to xhigh.
MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use.
MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of up to 1M tokens, and can also operate a desktop computer.
Mistral Large 4 is Mistral AI's general-purpose multimodal Mixture-of-Experts model, with 1.05 trillion total parameters, 52 billion active, and a 1.6B vision encoder. It takes text and image input and produces text output, and works as a hybrid instruct and reasoning model with function calling and structured outputs. It is built for coding, agentic workflows and multimodal understanding, and is natively fluent in more than 160 languages.
Inkling Small is a smaller model in Thinking Machines Lab's Inkling family, a Mixture-of-Experts with 276B total and 12B active parameters. Like Inkling, it accepts text, image and audio input and generates text, with a context of up to 1M tokens and variable thinking effort.
Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.
Grok 4.6 is xAI's model for coding, agentic tasks and knowledge work, designed for long, multi-step work such as research, codebase tasks and turning an idea into a working application. It takes text and image input and produces text output, with a 500K-token context window, function calling, structured outputs and low to xhigh reasoning effort.
Grok 4.7 is xAI's model for software engineering and professional knowledge work, especially long-running tasks. Compared with Grok 4.6 it uses a larger base model trained longer on harder tasks and checks its own output more carefully, and it takes text and image input with a 500K-token context window and low to xhigh reasoning effort.
GPT-5 is OpenAI's reasoning model for coding, reasoning and agentic tasks across domains, with configurable reasoning effort (minimal, low, medium and high). It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5 Mini is a faster, more cost-efficient version of OpenAI's GPT-5 reasoning model, suited to well-defined tasks, precise prompts and high-volume, low-latency workloads. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5 Nano is the fastest, lowest-cost version of OpenAI's GPT-5 reasoning model, suited to summarization and classification tasks. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5.1 is OpenAI's GPT-5 series model for coding and agentic tasks, with configurable reasoning effort that includes a non-reasoning setting. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5.3 Codex is OpenAI's coding model built on GPT-5.3 and optimized for agentic coding tasks in Codex and similar environments. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and low to xhigh reasoning effort.
GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use.
GPT-5.4 Nano is the lowest-cost GPT-5.4-class model from OpenAI, designed for simple, high-volume tasks where speed and cost matter most, such as classification and data extraction. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
Llama 4 Scout is Meta's natively multimodal Mixture-of-Experts model with 17B active parameters, 16 experts and 109B total parameters. It takes text and image input and produces text and code with a context window of up to 10M tokens, and is built for assistant chat and visual reasoning such as captioning and image question answering.
GPT-5.6 Luna is OpenAI's GPT-5.6 model for cost-sensitive, high-volume workloads, roughly matching the nano tier of earlier GPT-5 families. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to max.
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.
Aion 3.5 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. Compared with Aion 3.0 it doubles the context window to 256K tokens, with up to 32K output tokens.
Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
Gemma 4 31B is the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family, with about 30.7B parameters. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking, native function calling and pretraining on over 140 languages.
Gemma 4 31B Instruct Turbo is a faster serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Ling 3.1 Flash is inclusionAI's native hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 560B total and 25B active parameters that builds on Ling 3.0 Flash. It takes text input and output with a 1M-token context window, is designed for complex real-world tasks, and lets thinking be turned on or off.
Moonshot AI's open-weight multimodal agentic model has 1T total and 32B active parameters, built for long-horizon coding and tool use.
NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.
NVIDIA Nemotron 3.5 Super VL is an open multimodal model for agents that see, reason, and act. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, and adds reasoning and tool use on top.
Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.
Qwen3.5-397B-A17B is a multimodal Mixture-of-Experts model from Alibaba's Qwen team, with 397B total parameters and 17B active per token. It takes text, image and video input and produces text, with a 262K-token native context window (extendable to about 1M), a default thinking mode, tool calling and support for 201 languages and dialects.
Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.
Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.
HauhauCS's Aggressive adaptation of Qwen3.8-27B retains text and visual capabilities while modifying refusal behavior.
Qwen3 VL 30B A3B Instruct is a Mixture-of-Experts vision-language model from Alibaba's Qwen team. It takes text, image and video input and produces text with a native 256K-token context window, and handles visual agent tasks, visual coding, 2D and 3D grounding, long video understanding and OCR in 32 languages.
Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.
Hy3 is an open-weight Mixture-of-Experts language model from the Tencent Hy team, with 295B total parameters, 21B active per token and a 256K-token context window. It is a text model that combines fast and slow thinking, with selectable reasoning effort, and it supports tool calling. It is built for agentic work, coding, office tasks, financial modeling, frontend design and game development, and is released under Apache 2.0.
Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a native 262K-token context window and is built for agentic coding, tool calling and repository-scale work.
Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.
Seed 2.0 Code is the dedicated programming model in ByteDance Seed's Seed 2.0 family, built for software development and coding agents. It supports deep thinking and tool calling with a 256K-token context window and up to 128K output tokens.
Seed 2.0 Mini is the throughput-optimized model in ByteDance Seed's Seed 2.0 family, built for low-latency, high-concurrency and batch workloads. It supports multimodal understanding, tool calling and four thinking levels from minimal to high, with a 256K-token context window.
Seed 2.0 Pro is the general agent model in ByteDance Seed's Seed 2.0 family that focuses on long-chain reasoning and robustness in complex, multi-step workflows. It supports adjustable deep thinking, multimodal understanding and tool calling, with a 256K-token context window and up to 128K output tokens.
Seed 2.1 Turbo is one of ByteDance Seed's two Seed 2.1 models (with Pro), an agent model for general agents, end-to-end coding and multimodal understanding. It understands text, images and video with a 256K-token context window and supports deep thinking, GUI tasks, tool calling and structured output.
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.
Gemma 4 26B A4B Instruct is the Mixture-of-Experts model in Google DeepMind's open-weight Gemma 4 family, with 25.2B total and 3.8B active parameters per token. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Devstral 2 is Mistral AI's 123B dense transformer for agentic software engineering, released with open weights under a modified MIT license. It takes text input and produces text output, with a 256K context window. It is built to power coding agents that explore codebases, call tools and make coordinated edits across multiple files, for work such as bug fixing and modernizing legacy systems.
Mistral Large 3 is Mistral AI's open-weight multimodal granular Mixture-of-Experts model, with 675B total and 41B active parameters. It takes text and image input with a 256K-token context window and is built for agentic work, tool use, retrieval-augmented systems, long documents and coding across dozens of languages.
Mistral Small 3.2 is a 24B open-weight model from Mistral AI that accepts text and image input, released in June 2025 as a minor update to Mistral Small 3.1. It improves instruction following, produces fewer repetitive or infinite generations, and has a more robust function-calling template.
Mistral Small 4 is Mistral AI's open-weight hybrid model that unifies instruct, reasoning and coding capabilities in a single model. It is a Mixture-of-Experts model with 119 billion total parameters and 128 experts, 4 active per token, and a 256K-token context window. It accepts text and image input and produces text output, supports function calling and structured outputs, and offers a configurable reasoning effort for switching between fast replies and step-by-step reasoning on complex problems.
Kimi K2 Thinking is Moonshot AI's open-weight thinking model, a Mixture-of-Experts model with about 1 trillion total parameters and 32 billion active per token. It takes text input and produces text output, with a 256K-token context window. It is built to interleave step-by-step reasoning with function calls, and is designed to stay goal-directed across 200 to 300 sequential tool calls for research, coding and writing tasks.
Kimi K2.5 is Moonshot AI's open-weight, natively multimodal Mixture-of-Experts model with 1T total and 32B active parameters and a 256K-token context window. It accepts text and image input, offers thinking and instant modes, and is built for coding, visual coding, agent swarm workflows and office tasks.
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.
NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.
NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads.
GPT-5.2 is OpenAI's GPT-5 series model for complex professional work. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and reasoning effort from none to xhigh.
Qwen3-Coder-480B-A35B-Instruct is an open-weight coding model from Alibaba's Qwen team, a Mixture-of-Experts model with 480 billion total parameters and 35 billion active per token. It takes text input and produces text output, with a native context window of 262,144 tokens. It is built for agentic coding, browser use and tool calling, and runs in non-thinking mode only.
Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a native 262K-token context window and is built for agentic coding, tool calling and repository-scale work.
Qwen 3 Next 80B is a Mixture-of-Experts model from Alibaba's Qwen team with 80B total and 3B active parameters, using hybrid Gated DeltaNet and gated attention layers with multi-token prediction for efficient long-context work. It takes text input and output with a native 262K-token context window.
Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.
Qwen3 235B A22B Instruct 2507 is a text model.
Qwen3 Coder 30B A3B Instruct is an open-weight Mixture-of-Experts coding model from the Qwen team. It has 30.5B total parameters, with 3.3B active per token (8 of 128 experts), and a native 262,144-token context window. It is a text-only, non-thinking model built for agentic coding, agentic browser use and repository-scale code understanding, with a dedicated function-calling format, and is released under Apache 2.0.
Qwen3 Coder 480B A35B Instruct is a text model.
Qwen3 Coder Next is an open-weight coding model from Alibaba's Qwen team, built for coding agents and local development on the Qwen3-Next hybrid-attention Mixture-of-Experts architecture with 80B total and 3B active parameters. It has a native 262K-token context window and is aimed at agentic coding, tool calling and recovery from execution failures.
Qwen3 Next 80B A3B Instruct is a text model.
Qwen3-VL-235B-A22B-Thinking is the reasoning-enhanced Thinking edition of the Qwen team's Qwen3-VL vision-language series, a Mixture-of-Experts model with about 235 billion total parameters and 22 billion active. It accepts text, image and video input and produces text output. It is built for multimodal reasoning in STEM and math, visual agent tasks on PC and mobile interfaces, generating code from images or video, 2D and 3D grounding, and OCR in 32 languages.
xAI's fast coding model trained specifically for agentic coding, currently in early access.
GLM 4.7 Flash is a text model.
GLM-5.1 is Z.ai's open-weight Mixture-of-Experts model for agentic engineering, with 744B total and 40B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is tuned for coding agents and long-running tool use.
Claude Haiku 4.5 is Anthropic's small, fast model for real-time, low-latency work such as chat assistants, customer support agents and pair programming. It takes text and image input and produces text output, with a 200K-token context window, up to 64K output tokens and extended thinking.
Claude Sonnet 4.5 is a text model.
Gemini 2.5 Pro is Google's thinking model for reasoning over complex problems in code, math and STEM. It can analyze large datasets, codebases and documents using long context, taking text, image, video, audio and PDF input and producing text output, with a 1M-token context window and up to 65K output tokens.
o3 is OpenAI's well-rounded reasoning model for complex tasks across domains. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens.
o3-mini is OpenAI's small reasoning model, offering strong reasoning at the cost and latency targets of o1-mini. It takes text input and produces text output, with a 200K-token context window and up to 100K output tokens.
o4-mini is OpenAI's fast, cost-efficient reasoning model, optimized for efficient performance in coding and visual tasks. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens.
GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.
GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image and text inputs.
Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.
Gemma 3 27B Instruct is the 27-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
MiniMax-M2.5 is MiniMax's open-weight large language model for coding, agentic tool use and search, and office work. It takes text input and produces text output, and is built for complex multi-step agentic tasks and deliverable outputs such as Word, PowerPoint and Excel documents.
MiniMax-M2.7 is MiniMax's open-weight model of about 229B parameters, built for agentic and professional work. It handles software engineering (debugging, refactoring, code security), complex agent harnesses with tool search, and editing of Word, Excel and PowerPoint files.
GLM-4.6 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is built for agentic coding, front-end development, reasoning, writing and role-play.
GLM-4.7 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is built for agentic coding, UI generation, tool use, reasoning and writing.
GLM-5 is Z.ai's open-weight Mixture-of-Experts model with 744B total and 40B active parameters, built for complex systems engineering and long-horizon agentic tasks. It takes text input and output with a 200K-token context window and up to 128K output tokens.
MiniMax-M2 is MiniMax's open-weight Mixture-of-Experts language model built for coding and agentic workflows, with 230 billion total parameters and 10 billion active per token. It takes text input and produces text output, with a context window of 204,800 tokens. It is designed for multi-file edits, code-run-fix loops and test-validated repairs, and for long tool-calling sequences across shell, browser, retrieval and code-execution tools.
MiniMax-M2.1 is MiniMax's open-weight Mixture-of-Experts language model, an update to MiniMax-M2 focused on real-world coding and agentic tasks. It takes text input and produces text output. MiniMax highlights multi-language programming across Rust, Java, Go, C++, Kotlin, Objective-C, TypeScript and JavaScript, native Android and iOS development, web and app development, tool use and long-horizon planning, and multi-step office workflows.
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.
DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.
DeepSeek V3.1 is DeepSeek's hybrid Mixture-of-Experts model with 671B total and 37B active parameters, supporting both thinking and non-thinking modes in a single model. It has a 128K-token context window and improves tool calling and agent tasks over DeepSeek V3.
DeepSeek-V3.2 uses DeepSeek Sparse Attention for efficient long contexts, with strong reasoning and tool use.
Gemma 3 12B Instruct is the 12-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Gemma 3 4B Instruct is the 4-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Gemma 4 31B Instruct Ultra is a speed-optimized serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Granite 4.2 8B is IBM's 8B-parameter dense reasoning model in the open-weight Granite 4.2 family, for reasoning, code generation, tool calling and agentic workflows. It takes text input and produces text output with a 128K-token native context, and offers full thinking, non-thinking and low-effort thinking modes per request.
Ling 3.0 Flash is inclusionAI's hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 124B total and 5.1B active parameters built for efficient agentic workflows such as coding and deep research. It takes text input and output with a 256K-token context window, and its thinking mode can be turned off per request.
Ling 3.0 Flash VL is inclusionAI's multimodal version of Ling 3.0 Flash, a Mixture-of-Experts model with 124B total and 5.5B active parameters. It takes text, image and video input and produces text with a context of up to 256K tokens, and is built for document and chart understanding, GUI agents and long-video question answering.
Meta Llama 3.1 8B Instruct Turbo is a faster serving variant of Llama 3.1 8B Instruct, Meta's small multilingual instruction-tuned text model. The model has a 128K-token context window, officially supports eight languages and supports tool use.
Llama 3.3 70B is Meta's multilingual instruction-tuned text model, released in December 2024. It takes text input and produces text and code with a 128K-token context window, officially supports eight languages, and is built for assistant-style chat.
Llama 3.3 70B Instruct is Meta's 70B-parameter multilingual instruction-tuned model, tuned for assistant-style dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. It takes text input and produces text and code with a 128K-token context window. This Turbo variant is a faster serving variant of Llama 3.3 70B Instruct.
Muse Glimmer 30B is an open-weight multimodal model from Meta Superintelligence Lab, distilled from Muse Spark. It is a dense 30B transformer that takes text and image input and produces text with a context window of at least 131K tokens, built for local and coding agents, tool calling and multimodal reasoning on a single consumer GPU or Mac.
gpt-oss-120b is OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters, released under the Apache 2.0 license. It takes text input and produces text output with a 128K-token context window, configurable low, medium and high reasoning, full chain-of-thought access and native tool use including function calling and structured outputs.
GPT OSS 120B Ultra is a speed-optimized serving variant of gpt-oss-120b, OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters. The base model takes text input and produces text output with a 128K-token context window, configurable reasoning effort and native tool use.
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Aion 3.0 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. It takes text input and output with a 128K-token context window and up to 32K output tokens, and supports reasoning.
Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
Mercury 2 is Inception's diffusion-based reasoning language model, which generates by refining many tokens in parallel rather than one at a time. It takes text input and output with a 128K-token context window and supports tunable reasoning depth, native tool calling and schema-aligned JSON output.
Llama 3.2 3B is a small multilingual text model from Meta, instruction tuned for assistant-style chat and agentic tasks such as knowledge retrieval, summarization and prompt rewriting. It takes text input and produces text and code with a 128K-token context window, and officially supports eight languages.
Magistral Small 1.2 (2509) is Mistral AI's 24B open-weight reasoning model, fine-tuned from Mistral Small 3.2. It takes text and image input and produces text output, generating a reasoning trace before its final answer, with a 128K context window and support for 24 languages. It is built for multi-step reasoning tasks and is compact enough for local deployment once quantized.
Ministral 3 14B Instruct is the largest instruction-tuned model in Mistral AI's Ministral 3 family of dense open-weight models, combining a 13.5B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and multilingual support. It is built for private chat and assistant deployments, local agentic workflows and fine-tuning.
Ministral 3 3B Instruct is the instruction-tuned 3B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining a 3.4B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and support for 11 languages. It is built for edge and local deployment, and for tasks such as image captioning, classification, translation and data extraction.
Ministral 3 8B Instruct is the instruction-tuned 8B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining an 8.4B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and multilingual support. It is built for local assistants, chat in constrained environments, image and document understanding, and agentic use cases.
Mistral Uncensored Roleplay is an uncensored 24B fine-tune of Mistral Small 24B for character-driven roleplay, immersive storytelling and open-ended creative writing with minimal content restrictions. It accepts text and image input, supports function calling and has a 128K-token context window.
NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.
NVIDIA Nemotron Nano 12B v2 VL is an open 12.6B-parameter vision-language model from NVIDIA. It pairs a CRadioV2-H vision encoder with the Nemotron Nano 12B v2 language model. It takes English text, up to four images or a video as input and returns text, with 128K tokens of combined input and output context. It is built for document intelligence on invoices, receipts and manuals, visual question answering, summarization, multi-image reasoning and video understanding.
NVIDIA Nemotron Nano 9B v2 is an open 9B-parameter reasoning and chat model from NVIDIA, built on a hybrid Mamba-2 and Transformer architecture with only four attention layers. It was produced by pruning and aligning the 12B Nemotron Nano v2 base model. It handles text input and output with up to 128K tokens of context and supports tool calling. Reasoning is on by default and can be switched off, and an optional thinking budget caps reasoning tokens.
OpenAI's multimodal model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.
OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.
gpt-oss-safeguard-120b is an open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-120b, with 117B total parameters and 5.1B active. It classifies content against a safety policy that the developer writes and supplies at inference time, and it produces a reviewable chain of thought for each decision. It is built for trust and safety tasks such as input and output filtering and content labeling, supports low, medium and high reasoning effort, and is released under Apache 2.0.
gpt-oss-safeguard-20b is the smaller open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-20b, with about 21B total parameters and 3.6B active. It reads a developer-written safety policy at inference time and classifies content against it with a visible chain of thought, for lower-latency trust and safety tasks such as input and output filtering and content labeling. It supports low, medium and high reasoning effort and is released under Apache 2.0.
Qwen 3 235B A22B Instruct 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant runs in non-thinking mode only, answering directly without reasoning blocks, and has a native 262K-token context window.
Qwen 3 235B A22B Thinking 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant always thinks before answering, for complex reasoning tasks, and has a native 262K-token context window.
Qwen3-VL 235B A22B Instruct is Alibaba's Qwen vision-language Mixture-of-Experts model with about 236B total and 22B active parameters. It takes image, video and text input and produces text, with a native 256K-token context, OCR in 32 languages, GUI agent abilities and long-video understanding.
Free access to North Mini Code on limited shared capacity. Anonymous route; account opt-in required.
Free access to Dots3 Note Preview on limited shared capacity. Anonymous route; account opt-in required.
Free access to Beam on limited shared capacity. Anonymous route; account opt-in required.
Free access to GLM 4.5 Flash on limited shared capacity. Anonymous route; account opt-in required.
Qwen3 14B is a dense 14.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
Qwen3 30B A3B is a Mixture-of-Experts model in the Qwen3 family with 30.5B total and 3.3B active parameters from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
Qwen3 32B is a dense 32.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
Gemma 4 12B Instruct is the instruction-tuned 12B model in Google DeepMind's Gemma 4 family of open models. It is a dense 11.95B-parameter multimodal model with configurable thinking modes, native function calling, and support for over 140 languages.
Free access to Gemma 4 26B A4B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Mistral Small 3.1 24B on limited shared capacity. Anonymous route; account opt-in required.
Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.
Free access to Qwen3 30B A3B on limited shared capacity. Anonymous route; account opt-in required.
Voxtral Mini 3B is a text model.
Free access to GPT OSS 120B on limited shared capacity. Anonymous route; account opt-in required.
Free access to GPT OSS 20B on limited shared capacity. Anonymous route; account opt-in required.
Palmyra Vision 7B is a text model.
