Alternatives to North Mini Code
Compare North Mini Code alternatives for your business or organization using the curated list below. SourceForge ranks the best alternatives to North Mini Code in 2026. Compare features, ratings, user reviews, pricing, and more from North Mini Code competitors and alternatives in order to make an informed decision for your business.
-
1
Kimi K3.1 Pro
Moonshot AI
Kimi K3.1 Pro is a multimodal large language model developed by Moonshot AI for advanced reasoning, software development, 3D modeling, financial analysis, and autonomous AI agent workflows. The model uses a mixture-of-experts architecture with approximately 2.8 trillion total parameters and 104 billion active parameters, supporting a context window of one million tokens. Its coding capabilities include debugging existing applications, generating complete software projects, developing interactive websites, and creating applications with game engines. Kimi K3.1 Pro can analyze images, interpret spatial relationships, generate CAD scripts, and create three-dimensional assets from text descriptions or visual references. Its reasoning and tool-use capabilities support financial modeling, investment research, document analysis, and multistep business workflows. The model is available through Kimi's web and mobile applications, Kimi Work, Kimi Code, and the Kimi API, with a Highspeed variant.Starting Price: $2 per 1M tokens -
2
Muse Spark Open
Meta
Muse Spark Open is an open-weight, natively multimodal language model for developers and organizations building AI applications, coding systems, and agentic workflows. The released model has 816 billion total parameters, 42 billion active parameters, and a 1-million-token context window. Teams can download the model weights, run inference through supported engines such as vLLM, SGLang, TensorRT-LLM, Hugging Face Transformers, Apple MLX, llama.cpp, or Unsloth, and customize the model using PyTorch. It supports long-context reasoning, software engineering, coding, tool use, and multimodal inputs. Deployment options include cloud inference through listed API providers or self-hosting on compatible GPU systems; Meta documents a desktop setup using two Apple M5 Ultra Mac Studio computers. The model is released under the Muse Model License with limited commercial terms.Starting Price: $0 -
3
Nemotron 3.5 Bolt
NVIDIA
NVIDIA Nemotron 3.5 Bolt is a family of open artificial intelligence models designed for local AI agents, autonomous task execution, and conversational applications. The family includes Nemotron 3.5 Bolt 74B-A9B, a 74-billion-parameter mixture-of-experts model with approximately 9 billion active parameters, and Nemotron 3.5 Bolt E4B, a compact model optimized for conversational agents. The 74B-A9B variant uses native 2-bit quantization to operate within approximately 24GB of memory on compatible NVIDIA hardware. Its agentic capabilities support web research, software development, code debugging, and multistep task automation without requiring cloud-based inference. The E4B variant targets local voice assistants, interactive characters, and embedded applications with a 4GB memory footprint. Nemotron 3.5 Bolt supports deployment on NVIDIA RTX systems, DGX Spark, and other compatible hardware, giving developers greater control over inference, application data, and local AI workflows.Starting Price: Free -
4
Nemotron 3.5 Super VL
NVIDIA
NVIDIA Nemotron 3.5 Super VL is an open, customizable multimodal AI model designed for complex reasoning, autonomous agents, and enterprise workflows. The model uses a 120-billion-parameter mixture-of-experts architecture that activates approximately 12 billion parameters per token to balance computational efficiency with model capabilities. It combines text, image, document, and video understanding with instruction following, coding, and external tool use. Its multimodal capabilities support document analysis, chart interpretation, optical character recognition, video understanding, and automated information extraction. Developers can customize the model through supervised fine-tuning, low-rank adaptation, and reinforcement learning using NVIDIA NeMo. Nemotron 3.5 Super VL supports deployment in local, cloud, and data center environments for applications such as software engineering, financial document processing, cybersecurity analysis, and enterprise automation.Starting Price: $0 -
5
MiMo-V2.6-Pro
Xiaomi Technology
MiMo-V2.6-Pro is Xiaomi MiMo’s most capable open-source omnimodal AI model, built for coding, general agent workflows, visual tasks, research, and multimodal creation. The model combines strong software engineering capabilities with computer use, 3D spatial reasoning, visual perception, and tool use for complex multi-step work. MiMo-V2.6-Pro can build interactive 3D environments, generate Blender models, create frontend interfaces and presentations, and coordinate agents to refine outputs through visual feedback. It also supports research workflows such as literature review, computational experimentation, materials discovery, and formal mathematical proof development. Xiaomi trained the model with large-scale reinforcement learning across coding, general agents, visual tasks, and cybersecurity environments and has open-sourced the technical report, training environments, and RL code.Starting Price: Free -
6
GLM-5.2
Z.ai
GLM-5.2 is an advanced AI foundation model designed to support complex reasoning, coding, and long-range agentic tasks. It helps developers, teams, and organizations build intelligent systems that can understand instructions, solve technical problems, and assist with demanding workflows. The model is especially useful for software engineering, automation, research, and productivity-focused applications. GLM-5.2 is built to handle large amounts of context, making it suitable for projects that require deeper understanding across extended conversations, documents, or codebases. Its mixture-of-experts design helps balance strong performance with more efficient model operation. GLM-5.2 gives businesses and developers a powerful AI tool for creating smarter applications, improving technical workflows, and supporting advanced digital experiences.Starting Price: Free -
7
SWE-2
Cognition
SWE-2 is Cognition’s advanced coding model designed to improve software engineering performance while reducing the cost of agentic coding workflows. The model is post-trained from Kimi K3 and uses reinforcement learning to optimize multiple reasoning-effort levels within a single training run. SWE-2 is designed to explore codebases more selectively, begin implementation sooner, and complete tasks with fewer redundant reads and reasoning steps than earlier Cognition models. Its capabilities include code generation, debugging, test creation, verification, repository analysis, and complex terminal-based software engineering tasks. The model also emphasizes stronger engineering judgment, end-to-end test coverage, instruction following, and evidence-based verification of user assumptions. SWE-2 is available through Devin Desktop and Devin CLI, with broader rollout planned across Devin Web and Fusion.Starting Price: $20/month -
8
Qwen3.8-Max
Alibaba
Qwen3.8-Max is Qwen’s most capable model to date, built as a Max-class AI model for coding, work, research, long-horizon tasks, and multimodal agents. It scales to 2.4 trillion parameters with 95 billion active parameters and is available through QwenCloud. The model is designed to complete complex, open-ended tasks end to end with greater reliability and minimal human involvement. Qwen3.8-Max supports autonomous coding workflows, agentic development, research reproduction, visual reasoning, document understanding, video analysis, and real-world productivity tasks. It can integrate with popular agent frameworks and coding assistants, including Claude Code, Codex, Qoder CLI, Qwen Code, and OpenClaw. Built for developers, researchers, enterprises, and AI agent builders, Qwen3.8-Max helps teams automate sophisticated work across code, documents, tools, interfaces, and multimodal content.Starting Price: $2 per 1M (input) -
9
GLM-5.3
Z.ai
GLM-5.3 is Z.ai’s frontier coding model designed for complex software engineering, long-horizon agent tasks, and advanced post-training research. The model uses the same base model as GLM-5.2, with improvements coming from scaled post-training across more environments, more diverse tasks, and larger compute investment. GLM-5.3 delivers stronger coding performance, better task ownership, improved benchmark results, and greater efficiency across realistic development workflows. It is built to handle complex coding tasks, production-style engineering work, research environments, automation tasks, and agentic workflows that require multi-step execution. The model also shows emergent cyber capabilities in vulnerability discovery and exploitation-chain reasoning, with safety evaluation and hardening planned before open-weight release.Starting Price: Free -
10
Composer 2.5
Cursor
Composer 2.5 is the latest AI coding model released by Cursor, offering major improvements in intelligence, collaboration, and long-task performance compared to Composer 2. The model is designed to follow complex instructions more accurately while providing a smoother and more natural user experience during coding sessions. Cursor enhanced Composer 2.5 through larger-scale training, more advanced reinforcement learning environments, and improved behavioral tuning focused on communication and effort calibration. The model uses targeted reinforcement learning with textual feedback to correct specific mistakes during training, helping it avoid issues like invalid tool calls or poor coding behavior. Composer 2.5 was also trained using significantly more synthetic coding tasks, enabling it to handle increasingly difficult programming challenges and real-world development scenarios.Starting Price: $0.50/M input -
11
Kimi K2.7 Code
Moonshot AI
Kimi K2.7 Code is an open-source, coding-focused agentic AI model developed by Moonshot AI for long-horizon software engineering tasks. It is designed to improve coding performance, agent workflows, and real-world development assistance compared with earlier Kimi K2 versions. The model supports a 256K context window, making it useful for working with large codebases, long technical documents, and complex multi-step programming tasks. Kimi K2.7 Code is available through Kimi Code and API access, with OpenAI- and Anthropic-compatible options for easier integration into developer workflows. It is also listed on Hugging Face and supports deployment through inference engines such as vLLM, SGLang, and KTransformers. With improved agentic capabilities, long-context support, and reduced thinking-token usage compared with K2.6, Kimi K2.7 Code gives developers a flexible open-source option for AI-assisted coding.Starting Price: Free -
12
Muse Spark 1.2
Meta
Muse Spark 1.2 is Meta’s coding-focused model update designed to power Muse Code and improve software engineering workflows. The model is built for code generation, complex debugging, codebase understanding, long-horizon development tasks, and end-to-end developer workflows. Muse Spark 1.2 was co-trained with Muse Code to improve performance inside the terminal coding agent environment. It supports planning, goal conditioning, context compaction, subagent coordination, and iterative coding workflows across large repositories. The model was trained with expanded coding compute, diverse development environments, self-improvement loops, and long-running engineering tasks. Built for AI developers and software teams, Muse Spark 1.2 helps agents plan, write, validate, debug, and optimize code with greater autonomy.Starting Price: $1.25 per 1M tokens (input) -
13
Inkling
Thinking Machines Lab
Inkling is an open-weights multimodal AI model from Thinking Machines designed as a customizable foundation model for developers, researchers, and enterprises. The model is a Mixture-of-Experts transformer with 975 billion total parameters, 41 billion active parameters, and support for context windows up to 1 million tokens. Inkling was trained from scratch on text, images, audio, and video, giving it native capabilities across reasoning, coding, agentic tool use, vision, audio, factuality, and instruction following. It is built with controllable thinking effort so users can balance performance, latency, and token efficiency for different workloads. The model is available for fine-tuning on Tinker, with playground access, API availability through ecosystem partners, and full weights published on Hugging Face. Built for customization, Inkling gives teams an open-weights base model for building domain-specific AI systems, multimodal agents, coding workflows, research tools, and more.Starting Price: Free -
14
Laguna S 2.1
Poolside
Laguna S 2.1 is an open weight agentic coding model designed to pursue longer-horizon work and make effective use of reasoning. It uses a 118-billion-parameter Mixture-of-Experts architecture with 8 billion active parameters per token and supports a context window of up to one million tokens in both thinking and no-thinking modes. Its compact active size makes it suitable for complex work on local machines while remaining competitive with models many times larger on terminal, software-engineering, codebase-question-answering, and tool-use benchmarks. Laguna S 2.1 is built to keep working through difficult tasks with greater persistence, verification, and willingness to backtrack instead of declaring success too early. In demonstrated runs, it built and validated a browser rendering engine from an empty folder, optimized an agent harness for faster execution and substantially lower memory allocation, and completed extended mathematical research using the tools in its environment. -
15
Nemotron 3 Ultra
NVIDIA
Nemotron 3 Nano is a compact, open large language model in NVIDIA’s Nemotron 3 family, designed for efficient agentic reasoning, conversational AI, and coding tasks. It uses a hybrid Mixture-of-Experts Mamba-Transformer architecture that activates only a small subset of parameters per token, enabling low-latency inference while maintaining strong accuracy and reasoning performance. It has approximately 31.6 billion total parameters with around 3.2 billion active (3.6 billion including embeddings), allowing it to achieve higher accuracy than previous Nemotron 2 Nano while using less computation per forward pass. Nemotron 3 Nano supports long-context processing of up to one million tokens, enabling it to handle large documents, multi-step workflows, and extended reasoning chains in a single pass. It is designed for high-throughput, real-time execution, excelling in multi-turn conversations, tool calling, and agent-based workflows where tasks require planning, reasoning, and more. -
16
MiniMax M3
MiniMax
MiniMax M3 is an open-weight multimodal AI model designed for coding, agentic workflows, long-context reasoning, and complex automation tasks. The model combines frontier-level coding performance, native multimodal understanding, and a context window of up to 1 million tokens. MiniMax M3 uses MiniMax Sparse Attention to improve long-context efficiency while reducing compute requirements for large-scale inputs. It supports text, image, and video understanding, making it useful for workflows that combine code, documents, visual references, and tool-driven tasks. The model is built for repository-scale reasoning, software engineering, autonomous task execution, tool calling, and multi-step agent workflows. MiniMax M3 helps developers, AI teams, and enterprises build capable agents that can reason across large contexts and work with multimodal information.Starting Price: $0.30 per million input tokens -
17
DeepSeek-V4-Pro
DeepSeek
DeepSeek-V4-Pro is a large-scale Mixture-of-Experts (MoE) language model designed for advanced reasoning, coding, and long-context understanding. It features 1.6 trillion total parameters with 49 billion activated parameters, enabling high performance while maintaining efficiency. The model supports an exceptionally large context window of up to one million tokens, allowing it to process extensive documents and workflows. It uses a hybrid attention architecture to optimize long-context performance and reduce computational cost. DeepSeek-V4-Pro is trained on over 32 trillion tokens, improving its knowledge and reasoning capabilities. It also includes advanced optimization techniques for stability and faster convergence during training. The model supports multiple reasoning modes, allowing users to balance speed and accuracy based on their needs. Overall, it provides a powerful open-source solution for complex AI tasks and large-scale applications.Starting Price: $0.435 per 1M tokens (input) -
18
GLM-5.3-Flash
Z.ai
GLM-5.3-Flash is Z.ai’s natively multimodal model in the GLM-5 series (previously previewed as Ox Alpha), designed to deliver strong coding, agentic, visual, and knowledge-work performance at relatively low inference cost. It uses 320 billion total parameters with 18 billion active parameters, along with a hybrid architecture that combines sparse and linear attention to reduce the cost of long-context processing. The model supports context lengths of up to one million tokens and was trained on a 30-trillion-token multimodal corpus. GLM-5.3-Flash can reason across text, images, documents, interfaces, dashboards, and other visual information while using that feedback to refine its own outputs. Z.ai reports substantial gains over GLM-5.2 on coding and agentic benchmarks, including DeepSWE and AutomationBench, while approaching higher-cost frontier models on several evaluations.Starting Price: $0.15 per 1M tokens (input) -
19
Claude Haiku 4.5
Anthropic
Anthropic has launched Claude Haiku 4.5, its latest small-language model designed to deliver near-frontier performance at significantly lower cost. The model provides similar coding and reasoning quality as the company’s mid-tier Sonnet 4, yet it runs at roughly one-third of the cost and more than twice the speed. In benchmarks cited by Anthropic, Haiku 4.5 meets or exceeds Sonnet 4’s performance in key tasks such as code generation and multi-step “computer use” workflows. It is optimized for real-time, low-latency scenarios such as chat assistants, customer service agents, and pair-programming support. Haiku 4.5 is made available via the Claude API under the identifier “claude-haiku-4-5” and supports large-scale deployments where cost, responsiveness, and near-frontier intelligence matter. Claude Haiku 4.5 is available now on Claude Code and our apps. Its efficiency means you can accomplish more within your usage limits while maintaining premium model performance.Starting Price: $1 per million input tokens -
20
GLM-5.1
Z.ai
GLM-5.1 is the latest iteration of Z.ai’s GLM series, designed as a frontier-level, agent-oriented AI model optimized for coding, reasoning, and long-horizon workflows. It builds on the GLM-5 architecture, which uses a Mixture-of-Experts (MoE) design to deliver high performance while keeping inference costs efficient, and is part of a broader push toward open-weight, developer-accessible models. A core focus of GLM-5.1 is enabling agentic behavior, meaning it can plan, execute, and iterate across multi-step tasks rather than simply responding to single prompts. It is specifically designed to handle complex workflows such as debugging code, navigating repositories, and executing chained operations with sustained context. Compared to earlier models, GLM-5.1 improves reliability in long interactions, maintaining coherence across extended sessions and reducing breakdowns in multi-step reasoning.Starting Price: Free -
21
Devstral Small 2
Mistral AI
Devstral Small 2 is the compact, 24 billion-parameter variant of the new coding-focused model family from Mistral AI, released under the permissive Apache 2.0 license to enable both local deployment and API use. Alongside its larger sibling (Devstral 2), this model brings “agentic coding” capabilities to environments with modest compute: it supports a large 256K-token context window, enabling it to understand and make changes across entire codebases. On the standard code-generation benchmark (SWE-Bench Verified), Devstral Small 2 scores around 68.0%, placing it among open-weight models many times its size. Because of its reduced size and efficient design, Devstral Small 2 can run on a single GPU or even CPU-only setups, making it practical for developers, small teams, or hobbyists without access to data-center hardware. Despite its compact footprint, Devstral Small 2 retains key capabilities of larger models; it can reason across multiple files and track dependencies.Starting Price: Free -
22
Gemma 4
Google
Gemma 4 is an AI model introduced by Google and built on the Gemini architecture to deliver improved performance and flexibility. The model is designed to run efficiently on a single GPU or TPU, making it more accessible to developers and researchers. Gemma 4 enhances capabilities in natural language understanding and text generation, supporting a wide range of AI-driven applications. Its architecture allows it to handle complex tasks while maintaining efficient resource usage. Developers can use the model to build applications that rely on advanced language processing and automation. The design emphasizes scalability so that it can support both smaller projects and larger AI systems. By combining efficiency with powerful language capabilities, Gemma 4 helps advance the development of modern AI solutions.Starting Price: Free -
23
Kimi K2.6
Moonshot AI
Kimi K2.6 is a next-generation agentic AI model developed by Moonshot AI, designed to push forward real-world execution, coding, and multi-step reasoning beyond earlier K2 and K2.5 versions. It builds on a Mixture-of-Experts architecture and the multimodal, agent-first foundation of the Kimi series, combining language understanding, coding, and tool use into a single system capable of planning and executing complex workflows. It introduces deeper reasoning capabilities and significantly improved agent planning, allowing it to break down tasks, coordinate tools, and handle multi-file or multi-step problems with greater accuracy and efficiency. It supports advanced tool calling with high reliability, enabling integration with external systems such as web search or APIs, and includes built-in validation mechanisms to ensure correct execution formats.Starting Price: Free -
24
Laguna XS 2.1
Poolside
Laguna XS 2.1 is an upgraded open weight agentic coding model designed for long-horizon work on a local machine. It uses a 33-billion-parameter Mixture-of-Experts architecture with 3 billion activated parameters per token, retaining the same efficient architecture as Laguna XS.2 while improving multilingual software engineering and terminal-style task performance. The model is built to support coding agents that inspect repositories, reason through complex changes, use tools, execute commands, and continue working across extended tasks. It is served with a 256K context window, giving agents room to work with large codebases, lengthy histories, and multi-step workflows. Laguna XS 2.1 is supported by vLLM, SGLang, NVIDIA TensorRT-LLM, Hugging Face Transformers, and Ollama, with native llama.cpp support planned. It is available in BF16, FP8, INT4, and NVFP4 checkpoints, allowing developers to choose between maximum fidelity and configurations suited to tighter VRAM or compute budgets. -
25
Laguna XS.2
Poolside
Laguna XS.2 is Poolside’s open-weight agentic coding model, built as the lightest and fastest model in the Laguna family. It is a 33B total-parameter Mixture of Experts model with 3B activated parameters, trained completely in-house on 30T tokens. As Poolside’s newest generation model open to the community, Laguna XS.2 is a second-generation architecture and the company’s first open-weight model, built on the lessons learned from training Laguna M.1 across synthetic data and reinforcement learning. The model is designed for agentic coding workflows, where it can code, act, iterate quickly, and perform best inside Poolside’s coding agent. Laguna XS.2 is positioned as a strong model for rapid agentic iteration, especially for developers and teams that need a compact, efficient coding model rather than a heavier frontier system. It is released under an Apache 2.0 license, allowing the community to evaluate, fine-tune, quantize, serve, and build on the weights.Starting Price: Free -
26
Qwen3.6
Alibaba
Qwen3.6 is a large language model developed by Alibaba as part of its Qwen AI model family, designed for real-world applications and advanced reasoning tasks. It focuses on improving stability, usability, and performance compared to earlier versions. The model supports multimodal capabilities, allowing it to process and reason across text, images, and other data types. Qwen3.6 is particularly strong in coding and developer workflows, offering improved accuracy for complex programming tasks. It uses a mixture-of-experts architecture, enabling efficient performance while maintaining large-scale model capabilities. The model is designed to be deployable in production environments, including enterprise and cloud-based systems. It can be integrated into applications or run locally using open-weight variants. Overall, Qwen3.6 delivers a powerful, efficient, and versatile AI solution for modern use cases.Starting Price: Free -
27
Muse Spark
Meta
Muse Spark is a multimodal AI reasoning model developed by Meta as part of its push toward personal superintelligence. It integrates text, images, and tools to deliver advanced reasoning and interactive capabilities. The model supports features like visual chain-of-thought and multi-agent orchestration. Users can leverage Muse Spark for tasks such as problem-solving, content creation, and real-world troubleshooting. Its Contemplating mode enables multiple AI agents to reason in parallel for improved performance. Muse Spark also demonstrates strong capabilities in areas like health insights and visual understanding. Overall, it represents a significant step toward more intelligent and personalized AI systems. -
28
Muse Spark 1.3
Meta
Muse Spark 1.3 is an AI model with improved performance across agentic and coding tasks, designed to be smarter and more practical for real-world work. It sustains longer-horizon tasks by collaborating with users and managing multiple workflows in a single, long thread. Given an open-ended objective, it uses tools to build context across messy or conflicting sources, correct gaps in its plan, track what it has learned, and produce a final deliverable. It asks clarifying questions when prompts are ambiguous, requests help when stuck, and confirms before taking consequential actions. The model follows complex, long-form instructions more reliably, preserving detailed requirements across multi-step tasks without dropping constraints or drifting from the requested workflow. Improved multitasking allows it to map incoming prompts to the correct task even when users interrupt or redirect previous requests.Starting Price: $1.25 per 1M tokens (input) -
29
SWE-1.7
Cognition
SWE-1.7 is Cognition’s frontier software engineering model designed to deliver high intelligence at a lower rollout cost. The model is optimized for long-horizon agentic coding tasks, including debugging, feature implementation, codebase exploration, migrations, terminal workflows, and multilingual software engineering. SWE-1.7 was trained from a Kimi K2.7 base using large-scale reinforcement learning improvements across infrastructure, data quality, training stability, self-compaction, and long-running task execution. It is built to explore codebases thoroughly, probe edge cases, identify hidden requirements, and produce more complete end-to-end solutions. The model is available in Devin across web, desktop, and CLI through Cerebras at very high serving speeds. SWE-1.7 is positioned for developers and engineering teams that need cost-efficient frontier-level coding intelligence for complex real-world software work.Starting Price: $20/month -
30
Inkling 2 Small
Thinking Machines Lab
Inkling 2 Small is a multimodal AI model developed by Thinking Machines Lab for advanced reasoning, autonomous software engineering, visual understanding, and AI agent development. The model uses a mixture-of-experts architecture with 594 billion total parameters and 17 billion active parameters to balance intelligence and computational efficiency. It supports text and image inputs, a context window of up to one million tokens, and configurable reasoning effort for tasks requiring different levels of analysis. Its agentic capabilities enable autonomous code generation, debugging, website development, scientific research, and complex multistep workflows involving external tools. Inkling 2 Small also supports fine-tuning and reinforcement learning through Thinking Machines Lab's Tinker platform, allowing developers to customize the model for specialized applications.Starting Price: $0.30 per million input tokens -
31
Kimi K2
Moonshot AI
Kimi K2 is a state-of-the-art open source large language model series built on a mixture-of-experts (MoE) architecture, featuring 1 trillion total parameters and 32 billion activated parameters for task-specific efficiency. Trained with the Muon optimizer on over 15.5 trillion tokens and stabilized by MuonClip’s attention-logit clamping, it delivers exceptional performance in frontier knowledge, reasoning, mathematics, coding, and general agentic workflows. Moonshot AI provides two variants, Kimi-K2-Base for research-level fine-tuning and Kimi-K2-Instruct pre-trained for immediate chat and tool-driven interactions, enabling both custom development and drop-in agentic capabilities. Benchmarks show it outperforms leading open source peers and rivals top proprietary models in coding tasks and complex task breakdowns, while its 128 K-token context length, tool-calling API compatibility, and support for industry-standard inference engines.Starting Price: Free -
32
Qwen3.8-2.4T-A95B
Alibaba
Qwen3.8-2.4T-A95B is the largest open model in the Qwen3.8 family, bringing Qwen-Max-class capabilities to an open release. Built on the architectural foundation of Qwen3.5, it delivers substantial improvements across coding, professional work, research, and long-horizon agentic tasks, with a focus on carrying complex, multi-step work through to completion more reliably. The causal language model uses a mixture-of-experts architecture with 2.4 trillion total parameters and 95 billion activated parameters, including 512 experts with 10 routed and one shared expert active at a time. It supports a native context length of 262,144 tokens that can be extended to approximately 1.01 million tokens. Agent execution is strengthened through better autonomous planning and improved handling of environment feedback, while broader compatibility with popular agent harnesses and development tools simplifies integration into existing stacks. -
33
Kimi K2 Thinking
Moonshot AI
Kimi K2 Thinking is an advanced open source reasoning model developed by Moonshot AI, designed specifically for long-horizon, multi-step workflows where the system interleaves chain-of-thought processes with tool invocation across hundreds of sequential tasks. The model uses a mixture-of-experts architecture with a total of 1 trillion parameters, yet only about 32 billion parameters are activated per inference pass, optimizing efficiency while maintaining vast capacity. It supports a context window of up to 256,000 tokens, enabling the handling of extremely long inputs and reasoning chains without losing coherence. Native INT4 quantization is built in, which reduces inference latency and memory usage without performance degradation. Kimi K2 Thinking is explicitly built for agentic workflows; it can autonomously call external tools, manage sequential logic steps (up to and typically between 200-300 tool calls in a single chain), and maintain consistent reasoning.Starting Price: Free -
34
Qwen3.5
Alibaba
Qwen3.5 is a next-generation open-weight multimodal large language model designed to power native vision-language agents. The flagship release, Qwen3.5-397B-A17B, combines a hybrid linear attention architecture with sparse mixture-of-experts, activating only 17 billion parameters per forward pass out of 397 billion total to maximize efficiency. It delivers strong benchmark performance across reasoning, coding, multilingual understanding, visual reasoning, and agent-based tasks. The model expands language support from 119 to 201 languages and dialects while introducing a 1M-token context window in its hosted version, Qwen3.5-Plus. Built for multimodal tasks, it processes text, images, and video with advanced spatial reasoning and tool integration. Qwen3.5 also incorporates scalable reinforcement learning environments to improve general agent capabilities. Designed for developers and enterprises, it enables efficient, tool-augmented, multimodal AI workflows.Starting Price: Free -
35
Nemotron 3.5 Lightning
NVIDIA
NVIDIA Nemotron 3.5 Lightning is an open 30B-parameter mixture-of-experts model with 3B active parameters, designed for high-volume, low-latency execution in long-running and always-on AI agents. Built for the execution layer of agentic systems, it handles frequent tasks such as tool calls, output validation, routine commands, and subagent delegation while larger reasoning models focus on planning and orchestration. Its MoE architecture activates only a fraction of parameters for each token, combining the capacity of a larger model with lower compute requirements. The model is trained for popular agent harnesses and supports speculative decoding through multi-token prediction, DFlash, and DSpark to improve inference speed across different serving scenarios. It is available with BF16 and NVFP4 checkpoints and can run from local systems such as DGX Spark and GeForce RTX hardware to data center environments. -
36
Recursive Flint
Recursive
Recursive Flint is a 40-billion-parameter mixture-of-experts language model for agentic coding on local hardware. It activates about 2.5 billion parameters per token and supports reasoning, multi-turn tool use, and context windows up to 512,000 tokens. Developers can use Flint with coding agents to inspect codebases, fix bugs, implement features, and write tests while running inference on their own hardware. Its weights are published under the Apache 2.0 license. Flint works with llama.cpp, Ollama, Unsloth, LM Studio, vLLM, and SGLang; Recursive also provides rec, an inference engine optimized for Apple Silicon M4 Pro and M5 Pro/Max. Setup documentation and examples help developers run the model locally. Flint is for developers and technical teams that want to operate and adapt a code-focused model on their own systems. -
37
Qwen3.6-35B-A3B
Alibaba
Qwen3.5-35B-A3B is part of the Qwen3.5 “Medium” model series, designed as a highly efficient, multimodal foundation model that balances strong reasoning ability with practical deployment requirements. It uses a Mixture-of-Experts (MoE) architecture with 35 billion total parameters but activates only about 3 billion per token, allowing it to deliver performance comparable to much larger models while significantly reducing computational cost. The model integrates a hybrid attention mechanism that combines linear attention with standard attention layers, enabling efficient long-context processing and improved scalability for complex tasks. As a native vision-language model, it can process both text and visual inputs, supporting use cases such as multimodal reasoning, coding, and agent-based workflows. It is designed to function as a general-purpose “AI agent,” capable of planning, tool use, and structured problem solving rather than just conversational responses.Starting Price: Free -
38
Sarvam 105B
Sarvam
Sarvam-105B is the flagship large language model in Sarvam’s open source model family, designed to deliver high-performance reasoning, multilingual understanding, and agent-based execution within a single scalable system. Built as a Mixture-of-Experts (MoE) model with approximately 105 billion total parameters, of which only a fraction are activated per token, it achieves strong computational efficiency while maintaining high capability across complex tasks. The model is optimized for advanced reasoning, coding, mathematics, and agentic workflows, making it suitable for tasks that require multi-step problem solving and structured outputs rather than simple conversational responses. Sarvam-105B supports long-context processing of up to around 128K tokens, enabling it to handle large documents, extended conversations, and deep analytical queries without losing coherence.Starting Price: Free -
39
MiniMax M2
MiniMax
MiniMax M2 is an open source foundation model built specifically for agentic applications and coding workflows, striking a new balance of performance, speed, and cost. It excels in end-to-end development scenarios, handling programming, tool-calling, and complex, long-chain workflows with capabilities such as Python integration, while delivering inference speeds of around 100 tokens per second and offering API pricing at just ~8% of the cost of comparable proprietary models. The model supports “Lightning Mode” for high-speed, lightweight agent tasks, and “Pro Mode” for in-depth full-stack development, report generation, and web-based tool orchestration; its weights are fully open source and available for local deployment with vLLM or SGLang. MiniMax M2 positions itself as a production-ready model that enables agents to complete independent tasks, such as data analysis, programming, tool orchestration, and large-scale multi-step logic at real organizational scale.Starting Price: $0.30 per million input tokens -
40
MiniMax-M2.1
MiniMax
MiniMax-M2.1 is an open-source, agentic large language model designed for advanced coding, tool use, and long-horizon planning. It was released to the community to make high-performance AI agents more transparent, controllable, and accessible. The model is optimized for robustness in software engineering, instruction following, and complex multi-step workflows. MiniMax-M2.1 supports multilingual development and performs strongly across real-world coding scenarios. It is suitable for building autonomous applications that require reasoning, planning, and execution. The model weights are fully open, enabling local deployment and customization. MiniMax-M2.1 represents a major step toward democratizing top-tier agent capabilities.Starting Price: Free -
41
Inkling-Small
Thinking Machines Lab
Inkling-Small is an efficient model that offers performance comparable to Inkling at a quarter of its size. It is a Mixture-of-Experts transformer with 276 billion total parameters and 12 billion active parameters, trained on NVIDIA GB300 NVL72 systems. It supports native reasoning across text, images, and audio, variable thinking effort, and context windows of up to one million tokens. Users adjust reasoning effort from minimal to extra high to balance performance and compute. Improved pre-training data, post-training with on-policy distillation from Inkling, and extended agentic coding reinforcement learning helped Inkling-Small surpass its larger counterpart on reasoning and coding benchmarks. It performs well in coding and tool-use harnesses, exceeds 80% on SWE-bench Verified, and combines strong reasoning with efficient output. Its encoder-free multimodal architecture processes audio as dMel spectrograms and images as 40-by-40-pixel patches alongside text tokens.Starting Price: $0.30 per million input tokens -
42
Beam
Reflection
Beam is Reflection’s first open-weight model, a sparse Mixture-of-Experts model with 501 billion total parameters and 23 billion active parameters, built for coding, reasoning, and agentic workloads. Its capabilities come from large-scale pretraining and reinforcement learning, including training on 23.8 trillion diverse, curated, high-quality tokens from the web, public sources, and proprietary licensed datasets. Beam was trained with a particular focus on coding and agentic performance and is designed to deliver competitive open-weight capabilities with efficient inference compute. It supports complex software engineering, terminal, STEM, web search, tool-use, and general knowledge tasks, with reinforcement learning designed to improve multi-step reasoning, tool use, and adaptation to environment feedback. Users can control the tradeoff between performance and token usage through a reasoning effort parameter. -
43
MiniMax M2.5
MiniMax
MiniMax M2.5 is a frontier AI model engineered for real-world productivity across coding, agentic workflows, search, and office tasks. Extensively trained with reinforcement learning in hundreds of thousands of real-world environments, it achieves state-of-the-art performance in benchmarks such as SWE-Bench Verified and BrowseComp. The model demonstrates strong architectural thinking, decomposing complex problems before generating code across more than ten programming languages. M2.5 operates at high throughput speeds of up to 100 tokens per second, enabling faster completion of multi-step tasks. It is optimized for efficient reasoning, reducing token usage and execution time compared to previous versions. With dramatically lower pricing than competing frontier models, it delivers powerful performance at minimal cost. Integrated into MiniMax Agent, M2.5 supports professional-grade office workflows, financial modeling, and autonomous task execution.Starting Price: Free -
44
Nemotron 3
NVIDIA
NVIDIA Nemotron 3 is a family of open large language models developed by NVIDIA to power advanced reasoning, conversational AI, and autonomous AI agents. The Nemotron 3 series includes three models designed for different scales of AI workloads while maintaining high efficiency and accuracy. These models focus on “agentic AI” capabilities, meaning they can perform multi-step reasoning, coordinate with tools, and operate as components within multi-agent systems used in automation, research, and enterprise applications. The architecture uses a hybrid mixture-of-experts (MoE) design combined with transformer-based techniques, allowing the model to activate only a subset of parameters for each task, which improves performance while reducing computational cost. Nemotron 3 models are built to deliver strong reasoning, conversational, and planning abilities while maintaining high throughput for large-scale deployment. -
45
Leanstral
Mistral AI
Leanstral is an open-source code agent developed by Mistral AI specifically designed to work with the Lean 4 proof assistant. The model focuses on generating code while also formally verifying its correctness against strict mathematical or software specifications. Unlike traditional coding assistants, Leanstral integrates directly with formal proof systems to ensure that generated code satisfies defined logical requirements. Its architecture is optimized for proof engineering tasks and operates efficiently with sparse model parameters. Leanstral is released under the Apache 2.0 license, making it freely accessible for developers, researchers, and organizations to use and customize. The model is designed to operate within real-world formal repositories rather than isolated problem environments. By combining code generation with formal verification, Leanstral aims to reduce the need for manual human review in complex software and mathematical development.Starting Price: Free -
46
Qwen3.6-27B
Alibaba
Qwen3.6-27B is a dense, open source multimodal language model in the Qwen3.6 series, designed to deliver flagship-level performance in coding, reasoning, and agent-based workflows while maintaining a relatively efficient parameter size of 27 billion. It is positioned as a high-performance general model that “punches above its weight,” achieving results competitive with or superior to significantly larger models on key benchmarks, particularly in agentic coding tasks. It supports both thinking and non-thinking modes, allowing it to dynamically balance deep reasoning with fast responses depending on the task, and integrates capabilities across text and multimodal inputs such as images and video. Built as part of the Qwen3.6 family, the model emphasizes real-world usability, stability, and developer productivity, incorporating improvements driven by community feedback and practical deployment needs.Starting Price: Free -
47
DeepSeek R1
DeepSeek
DeepSeek-R1 is an advanced open-source reasoning model developed by DeepSeek, designed to rival OpenAI's Model o1. Accessible via web, app, and API, it excels in complex tasks such as mathematics and coding, demonstrating superior performance on benchmarks like the American Invitational Mathematics Examination (AIME) and MATH. DeepSeek-R1 employs a mixture of experts (MoE) architecture with 671 billion total parameters, activating 37 billion parameters per token, enabling efficient and accurate reasoning capabilities. This model is part of DeepSeek's commitment to advancing artificial general intelligence (AGI) through open-source innovation.Starting Price: Free -
48
MiniMax M2.7
MiniMax
MiniMax M2.7 is an advanced AI model designed to enhance real-world productivity across coding, search, and office workflows. It is trained with reinforcement learning across numerous real-world environments, enabling it to handle complex, multi-step tasks effectively. The model excels in problem-solving by breaking down challenges before generating solutions across multiple programming languages. It delivers high-speed performance with rapid token generation, allowing tasks to be completed efficiently. With optimized reasoning and cost-effective pricing, it provides powerful capabilities while minimizing resource usage. It also achieves strong performance in software engineering benchmarks, reducing incident response time and improving development efficiency. Additionally, it supports advanced agentic workflows and professional-grade office tasks, making it highly versatile for modern work environments.Starting Price: Free -
49
DeepSeek-V2
DeepSeek
DeepSeek-V2 is a state-of-the-art Mixture-of-Experts (MoE) language model introduced by DeepSeek-AI, characterized by its economical training and efficient inference capabilities. With a total of 236 billion parameters, of which only 21 billion are active per token, it supports a context length of up to 128K tokens. DeepSeek-V2 employs innovative architectures like Multi-head Latent Attention (MLA) for efficient inference by compressing the Key-Value (KV) cache and DeepSeekMoE for cost-effective training through sparse computation. This model significantly outperforms its predecessor, DeepSeek 67B, by saving 42.5% in training costs, reducing the KV cache by 93.3%, and enhancing generation throughput by 5.76 times. Pretrained on an 8.1 trillion token corpus, DeepSeek-V2 excels in language understanding, coding, and reasoning tasks, making it a top-tier performer among open-source models.Starting Price: Free -
50
Qwen2
Alibaba
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud. Qwen2 is a series of large language models developed by the Qwen team at Alibaba Cloud. It includes both base language models and instruction-tuned models, ranging from 0.5 billion to 72 billion parameters, and features both dense models and a Mixture-of-Experts model. The Qwen2 series is designed to surpass most previous open-weight models, including its predecessor Qwen1.5, and to compete with proprietary models across a broad spectrum of benchmarks in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning.Starting Price: Free
