Models

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model, building on Kimi K3 with enhanced post-training for advanced reasoning and autonomous task execution. It features a 1M-token context window and native image and video understanding, enabling complex, long-context multimodal workflows. Optimized for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, Kimi K3.1 Pro is well suited for autonomous software engineering, multimodal analysis, and complex professional workflows that require sustained reasoning and reliable execution.

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek’s cost-efficient Mixture-of-Experts (MoE) model, built on its innovative Causal Encoder-Decoder (CED) architecture. Featuring 552B total parameters with 8B activated for input and 16B for output, it combines efficient inference with native multimodal understanding through jointly trained text and visual representations. Optimized for coding, terminal and computer-use agents, and long-horizon workflows, the model introduces compressed KV caching that reduces cache memory usage to approximately one-quarter of the previous Flash generation. DeepSeek reports that it surpasses V4 Pro in performance, inference speed, and task completion time, making it well suited for cost-efficient autonomous agents, complex software engineering, and long-context analysis.

NVIDIA Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts (MoE) model featuring 120B total parameters with 12B activated per token. Built on a hybrid Mamba–Transformer architecture with multi-token prediction, it supports text, images, documents, GUI screenshots, and video inputs, along with a 1M-token context window for complex, long-horizon workflows. Optimized for multimodal reasoning, visual understanding, and agentic tool use, the model supports configurable reasoning modes and token budgets. It is well suited for document intelligence, web research, coding validation, customer service, GUI analysis, and video understanding, enabling efficient, long-running multimodal agent applications.

NVIDIA Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts (MoE) model featuring 120B total parameters with 12B activated per token. Built on a hybrid Mamba–Transformer architecture with multi-token prediction, it supports text, images, documents, GUI screenshots, and video inputs, along with a 1M-token context window for complex, long-horizon workflows. Optimized for multimodal reasoning, visual understanding, and agentic tool use, the model supports configurable reasoning modes and token budgets. It is well suited for document intelligence, web research, coding validation, customer service, GUI analysis, and video understanding, enabling efficient, long-running multimodal agent applications.

Muse Spark Open is an open-weight, coding-optimized model designed for agentic software engineering workflows. It delivers strong first-attempt accuracy, reliable tool calling, and deep codebase understanding, enabling effective development across real-world repositories. Optimized for autonomous coding agents, complex code navigation, and tool-driven development, Muse Spark Open is well suited for software engineering automation, debugging, code generation, and multi-step coding workflows where accuracy and reliable execution are essential.

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

Muse Wonder is Meta’s frontier multimodal reasoning model, designed for complex personal and professional agentic workflows. It supports text, image, video, audio, and PDF inputs with text output and features a 1M-token context window for sustained reasoning across long-running tasks. Optimized for autonomous execution and multi-agent orchestration, Muse Wonder can plan, delegate to subagents, coordinate parallel tool use, recover from errors, and operate browsers and applications across desktop and mobile environments. With cross-conversation context retrieval and its Active Focus training approach, it is well suited for complex software engineering, multi-file refactoring, computer use, and end-to-end workflows requiring persistence, adaptability, and minimal supervision.

GPT-6.1 Sol is an upgraded high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra. It is optimized for agentic coding, computer use, document-heavy professional work, and multi-step business automation, delivering near-Astra-level capability at significantly lower cost. Compared with GPT-6 Sol, it offers improved factual reliability and stronger adherence to explicit constraints and user intent, making it well suited for complex, long-running agentic workflows where accurate and dependable execution is critical.

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, serving as a direct upgrade to Sonnet 5. It excels at feature development, bug fixing, and creating polished documents, presentations, and spreadsheets, while offering clearer writing and communication than its predecessor.

Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.

GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. It combines Luna's speed and cost efficiency with deeper reasoning and more reliable multi-step execution, making it well suited for advanced coding, computer use, and agentic workflows where higher solution quality is needed without moving to a larger GPT-6 tier.

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, optimized for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks. It combines low-cost, responsive inference with the GPT-6 family’s improvements in factual reliability and clear, concise communication. At higher reasoning effort, GPT-6 Luna can also handle complex software engineering and computer-use workflows that previously required a Sol-tier model, making it a versatile choice for scalable production applications that need to balance speed, cost, and capability.

GPT-6 Sol Pro uses the same underlying model as GPT-6 Sol, but runs with reasoning.mode set to pro for higher-quality responses on complex and demanding tasks. Optimized for deeper reasoning, greater accuracy, and more reliable multi-step execution, it is particularly well suited for agentic coding, long-horizon software engineering, professional analysis, and complex automated workflows where solution quality takes priority over latency and cost.

GPT-6 Sol is OpenAI's cost-efficient high-end model in the GPT-6 series, positioned between the flagship GPT-6 Astra and the fast GPT-6 Luna tier. It is designed for professional knowledge work, agentic coding, business workflow automation, and computer-use tasks, with particular strength in long-horizon software engineering across real-world codebases. GPT-6 Sol approaches Astra-level factual reliability at a significantly lower cost, while sharing its clear and concise communication style. This balance of capability, reliability, and efficiency makes it well suited for production agents, complex engineering workflows, and scalable professional applications

Claude Opus 5.5 is Anthropic's flagship model for advanced reasoning, coding, and long-horizon agentic workflows, succeeding Opus 5. It excels at multi-step changes across large codebases, code review and bug detection, financial and scientific analysis, and understanding dense charts, diagrams, and screenshots, with stronger grounding when reporting figures and citing sources. Compared with Opus 5, it completes comparable tasks with fewer steps and lower token usage while providing clearer, more concise progress reporting. With adaptive thinking and configurable effort levels, Opus 5.5 can balance reasoning depth, latency, and cost, making it well suited for both demanding autonomous workflows and latency-sensitive professional tasks.

Grok 4.7 is SpaceXAI's flagship model for coding, agentic workflows, and professional knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering, self-verification, and long-context execution, while improving capabilities in document drafting, presentations, and other professional tasks. Trained with extended reinforcement learning focused on multi-hour problems, Grok 4.7 is optimized for sustained, complex task execution and natively supports the Grok Bot harness for conversational workflows. It also introduces an enhanced safeguard stack designed to combine strong jailbreak resistance with low refusal rates for legitimate technical work. Reported benchmark results use xhigh reasoning effort.

DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion.

GPT-6 Astra Pro uses the same underlying model as GPT-6 Astra, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. Optimized for deeper reasoning, greater accuracy, and more reliable multi-step execution, it is well suited for demanding coding, analysis, and agentic workflows where solution quality takes priority over speed and cost.

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end professional work, designed for advanced analysis, software engineering, deep research, scientific tasks, and document creation. It is particularly strong in long-horizon agentic workflows, including tasks that require sustained reasoning, tool orchestration, and computer and browser use, making it well suited for complex autonomous workflows and production-grade knowledge work.

Muse Spark 1.3 is Meta's multimodal reasoning model designed for long-running agentic, multi-agent, and coding workflows. It maintains context and information across extended tasks, enabling reliable execution in complex, multi-step environments. The model is optimized to resolve conflicting information, seek clarification or confirmation when necessary, and execute concisely, making it well suited for autonomous agents, collaborative multi-agent systems, and long-horizon software engineering workflows.

Gemini 3.8 Flash is Google's most intelligent Flash-class model, delivering significant improvements over Gemini 3.7 Flash across software engineering, agentic workflows, and complex multi-step reasoning. Designed to combine strong capability with Flash-tier efficiency, it is well suited for coding assistants, autonomous agents, and high-throughput production workflows that require responsive performance without sacrificing reasoning quality.

Claude Fable 5.1 is an upgraded version of Fable 5, delivering broad improvements with particularly strong gains in agentic coding, long-running workflows, and professional knowledge work. It excels at large code refactors, front-end and visual code generation, financial analysis, and complex analytical tasks. Compared with Fable 5, it also produces more concise plans and summaries while maintaining strong performance across extended tasks, making it a natural upgrade for existing Fable workflows and a strong option alongside Opus 5 for reasoning-intensive applications.

Tencent Hy4 Preview is a Mixture-of-Experts (MoE) model from Tencent, featuring 770B total parameters with 49B activated per token. It is designed for coding agents, complex tool-driven workflows, and professional productivity tasks that require strong planning and reliable execution. Optimized for context continuity and sustained multi-step work, Hy4 Preview is well suited for long-horizon coding, agentic automation, tool orchestration, and complex real-world workflows.

GLM-5.3-Flash is Z.AI's efficient native multimodal model, designed for coding and long-horizon agentic workflows. It combines strong multimodal capabilities with an architecture optimized for responsive, cost-efficient task execution. Built on a hybrid sparse and linear attention architecture, GLM-5.3-Flash maintains accurate long-context behavior while reducing computational overhead, making it well suited for coding agents, extended multi-step tasks, and scalable production workloads.

GLM-5.3 is Z.ai's large-scale reasoning model designed for complex software engineering and long-horizon agentic workflows. It supports text input and output with a 1M-token context window, enabling sustained reasoning across large codebases and extended multi-step tasks. Building on GLM-5.2, it delivers stronger coding performance while improving the balance between capability and token efficiency, making it well suited for autonomous coding agents, large-scale engineering workflows, and complex task execution.

Gemini 3.7 Flash is Google's fast multimodal model designed for agentic workflows, coding, and complex multi-step reasoning. It combines responsive inference with reliable problem-solving capabilities, making it well suited for interactive and production-scale applications. Optimized for speed and dependable multi-step execution, Gemini 3.7 Flash is a strong choice for coding assistants, autonomous agents, and high-throughput workflows that require both low latency and capable reasoning.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen, designed for coding, professional knowledge work, research, and multimodal interaction. It combines strong text and visual understanding with capabilities optimized for sustained, real-world agentic tasks. The model supports flexible thinking modes that can be enabled for deeper reasoning or disabled for faster execution, making it well suited for long-running agents, multimodal workflows, coding assistants, and cost-conscious self-hosted deployments.

Qwen3.8 2.4T A95B is Qwen's open-weight sparse Mixture-of-Experts (MoE) model and the open-weight counterpart to Qwen3.8 Max. It features 2.4T total parameters with 95B activated per token, combining frontier-scale capacity with efficient sparse inference. Designed for coding, research, complex reasoning, and agentic workflows, the model is well suited for demanding long-horizon tasks and advanced autonomous systems while providing the flexibility and customization benefits of open weights.

Grok 4.6 is SpaceXAI's smartest frontier model, delivering top-tier performance across coding, knowledge work, and STEM reasoning. It is designed for demanding technical and professional workloads that require strong problem solving, accurate instruction following, and reliable execution. Optimized for software engineering, scientific analysis, and complex knowledge tasks, Grok 4.6 is well suited for advanced coding, research, and agentic workflows where high capability and reasoning quality are critical.

DeepSeek V4 Pro 0813 is DeepSeek's large-scale Mixture-of-Experts (MoE) model and the general availability (GA) release of DeepSeek V4 Pro. It is designed for high-capability workloads requiring advanced reasoning, coding, and agentic task execution. As the production-ready V4 Pro release, it is well suited for complex software engineering, long-horizon agent workflows, and demanding reasoning tasks where reliability and model capability are critical.

NVIDIA Nemotron 3.5 Lightning is an open Mixture-of-Experts (MoE) model with 30B total parameters and 3B active per token, optimized for high-throughput agentic workloads and efficient inference. Its lightweight active compute and open design make it well suited for specialized agents, domain-specific customization, and scalable production deployments where speed, cost efficiency, and adaptability are key.

NVIDIA Nemotron 3.5 Lightning is an open Mixture-of-Experts (MoE) model with 30B total parameters and 3B active per token, optimized for high-throughput agentic workloads and efficient inference. Its lightweight active compute and open design make it well suited for specialized agents, domain-specific customization, and scalable production deployments where speed, cost efficiency, and adaptability are key.

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It combines strong multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across 100+ languages. Designed for long-horizon agentic and coding workflows, Muse Glimmer 30B offers a practical balance of capability and deployment efficiency, making it well suited for local coding assistants, multimodal agents, and production workflows that require sustained autonomous execution.

Muse Spark 1.2 is Meta's multimodal reasoning model designed for complex agentic and software engineering workflows. It supports text, image, video, audio, and PDF inputs with text output, and features a 1M-token context window for sustained reasoning across large, multi-stage tasks. Built for flexible multi-agent execution, Muse Spark 1.2 can serve as either a coordinating main agent or a parallel task-focused subagent. With configurable reasoning effort, structured outputs, parallel function calling, and broad coding-harness compatibility, it is well suited for multi-file refactoring, extended debugging, whole-repository generation, and long-horizon development workflows.

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series and the general-availability successor to Qwen3.8 Max Preview. It is a multimodal reasoning model designed for complex tasks across reasoning, visual understanding, coding, and agentic workflows. As the production-ready top tier of the Qwen3.8 family, it is well suited for advanced problem solving, multimodal analysis, software engineering, and long-running tool-driven applications.

Claude Opus 5 (Fast) is the fast version of Opus 5 model.

Qwen3.7 Flash is Alibaba's vision-language reasoning model, designed for multimodal agents, visual coding, search, and computer interaction. It combines fast inference with strong visual understanding, including object recognition, spatial reasoning, and real-world scene perception. Optimized for interactive and agentic workflows, Qwen3.7 Flash is well suited for GUI understanding, visual question answering, multimodal search, and computer-use applications that require responsive reasoning across text and images.

Claude Opus 5 is Anthropic's flagship model for advanced reasoning, coding, and long-horizon agentic workflows. It excels at end-to-end software engineering, code review, bug detection, visual analysis of charts and documents, complex office deliverables, and parallel subagent coordination. The model maintains reliable instruction following and tool use across extended tasks, while remaining effective at lower reasoning-effort settings for workloads that prioritize latency and token efficiency.

Gemini 3.5 Flash-Lite is Google's high-efficiency model with enhanced agentic capabilities, optimized for fast, cost-effective inference. It is designed to handle focused tasks with low latency while maintaining strong reasoning and execution quality. Well suited for subagents in complex multi-agent systems, Gemini 3.5 Flash-Lite excels at executing specialized tasks within larger workflows, making it ideal for scalable agent orchestration and high-throughput production environments.

Gemini 3.6 Flash is Google's high-efficiency model for coding, agentic workflows, and web and application development. It is optimized to produce polished, production-ready outputs with fewer unnecessary revisions, less hedging, and more direct task execution. By reducing both token usage and the number of model calls required to complete complex tasks, Gemini 3.6 Flash is well suited for high-throughput development, scalable agent systems, and cost-sensitive production workflows.

Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model, designed for complex coding, knowledge work, and long-horizon agentic workflows. It excels at repository-scale development, tool use, debugging, and iterative problem solving across text, images, logs, tests, and runtime feedback. Built with KDA and Attention Residuals for improved computational efficiency, Kimi K3 delivers strong performance on advanced engineering and multimodal reasoning tasks, making it well suited for autonomous coding agents and large-scale production workflows.

GPT-5.6 Terra Pro uses the same underlying model as GPT-5.6 Terra, but runs with reasoning.mode set to pro to deliver higher-quality responses on complex tasks. Optimized for deeper reasoning and greater reliability, it is well suited for advanced coding, multi-step reasoning, and agentic workflows where improved accuracy and solution quality are more important than maximizing speed or minimizing cost.

GPT-5.6 Luna Pro uses the same underlying model as GPT-5.6 Luna, but runs with reasoning.mode set to pro to deliver higher-quality responses on complex tasks. It is optimized for deeper reasoning, advanced coding, and multi-step agentic workflows, offering improved accuracy and solution quality while retaining the efficiency and scalability of the Luna tier.

GPT-5.6 Sol Pro uses the same underlying model as GPT-5.6 Sol, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. Optimized for deeper reasoning and more reliable execution, it is particularly well suited for advanced coding, long-horizon problem solving, and agentic workflows where accuracy and solution quality take priority over speed and cost.

GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is designed for everyday coding, reasoning, and agentic workflows, delivering strong performance while balancing capability and cost. Offering near-flagship quality at approximately half the cost of Sol, GPT-5.6 Terra is well suited for production applications that require reliable reasoning, software development, and scalable agent execution.

GPT-5.6 Luna is the fast, cost-efficient model in OpenAI's GPT-5.6 series, optimized for high-volume, latency-sensitive workloads. It delivers capable reasoning at an affordable price point, making it ideal for chat applications, classification, and lightweight agentic workflows. Designed for scalable production deployments, GPT-5.6 Luna balances speed, cost, and reliability, providing efficient performance for real-time applications and large-scale automation tasks.

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series, designed for complex reasoning, coding, and agentic workflows. It delivers strong performance on multi-step software engineering tasks, command-line workflows, and long-horizon problem solving, making it well suited for advanced development and autonomous execution. Optimized for high-reliability reasoning and end-to-end task completion, GPT-5.6 Sol excels in coding, tool-driven automation, and large-scale engineering workflows that require sustained context and precise execution.

Grok 4.5 is SpaceXAI’s flagship frontier model, delivering top-tier performance across coding, knowledge work, and STEM reasoning. Designed for demanding professional and technical workloads, it combines strong reasoning, accurate instruction following, and robust problem-solving capabilities. Optimized for software engineering, scientific analysis, and complex knowledge tasks, Grok 4.5 is well suited for advanced coding, research, and agent-driven workflows that require high accuracy and reliable long-horizon reasoning.

Hy3 is Tencent's 295B-parameter Mixture-of-Experts (MoE) model, activating 21B parameters per token across 192 experts, and designed for reasoning, agentic workflows, and production-scale applications. It supports a 256K-token context window and configurable reasoning modes, including no-think, low, and high reasoning effort to balance speed and problem-solving depth. Optimized for long-horizon tasks, coding, and tool-driven execution, Hy3 delivers strong performance in multi-turn reasoning, constraint tracking, and stable tool calling. With an emphasis on grounded responses and reduced hallucinations, it is well suited for software development, document processing, financial analysis, game development, and enterprise agent workflows.

Sonnet 5 is Anthropic's most capable Sonnet-class model, delivering frontier-level performance across coding, agentic workflows, and professional knowledge tasks. It supports text, image, and file inputs, features a 1M-token context window, and offers adaptive thinking with configurable reasoning levels (low, medium, high, max, and x-high) to balance speed, cost, and reasoning depth. Optimized for complex coding, long-horizon agent execution, and professional workflows, Sonnet 5 combines strong reasoning, robust instruction following, and enhanced safety features, including an updated tokenizer and real-time cyber safeguards for high-risk dual-use scenarios.