Free Models Monitor

Last updated: 2026-10-15T18:43:32Z · 26 models listed (15 OpenRouter · 11 OpenCode) · Sources: OpenRouter API · OpenCode models · Markdown overview · History

Currently listed

Free Models MonitorAPP15/10/2026 18:43

OpenCode: Big PickleOpenCode

ID:  opencode/big-pickle
🧠 80💻 79
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Context Length200,000 tokens
Max Completion32,000 tokens
ModalitiesInput: text
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: Cat Jam FreeOpenCode

ID:  opencode/cat-jam-free
🧠 89💻 84
A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.
Context Length262,144 tokens
Max Completion131,072 tokens
ModalitiesInput: text
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

✨ New Free Model Added: OpenCode: DeepSeek V4.1 Flash FreeOpenCodeNEW

ID:  opencode/deepseek-v4.1-flash-free
🧠 80💻 84
DeepSeek V4.1 Flash model for reasoning and agentic coding
Context Length200,000 tokens
Max Completion32,000 tokens
ModalitiesInput: text, image
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: LongCat 2.5 Preview FreeOpenCode

ID:  opencode/longcat-2.5-preview-free
🧠 92💻 89
Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window
Context Length1,000,000 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: MiMo-V2.6-Flash FreeOpenCode

ID:  opencode/mimo-v2.6-flash-free
🧠 75💻 74
MiMo Flash model for multimodal coding agents and long-context automation
Context Length200,000 tokens
Max Completion32,000 tokens
ModalitiesInput: text, image, audio, video
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: Muse Spark 1.2 FreeOpenCode⚠️ DEPRECATED

ID:  opencode/muse-spark-1.2-contributor-free
🧠 96💻 99
Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.
Context Length1,048,576 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image, video, pdf, audio
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: Muse Spark 1.3 FreeOpenCode

ID:  opencode/muse-spark-1.3-contributor-free
🧠 96💻 99
Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.
Context Length1,048,576 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image, video, pdf, audio
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: Nemotron 3.5 Lightning FreeOpenCode

ID:  opencode/nemotron-3.5-lightning-free
🧠 93💻 85
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Context Length262,144 tokens
Max Completion262,144 tokens
ModalitiesInput: text
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

✨ New Free Model Added: OpenCode: Nemotron 3.5 Super VL FreeOpenCodeNEW

ID:  opencode/nemotron-3.5-super-vl-free
🧠 92💻 89
NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use
Context Length1,048,576 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: Space Bunny FreeOpenCode

ID:  opencode/space-bunny-free
🧠 90💻 90
Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input
Context Length1,048,576 tokens
Max Completion524,288 tokens
ModalitiesInput: text, image, video
Output: text
Supported Parameterstools, tool_choice, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

OpenCode: Step 5 Preview FreeOpenCode

ID:  opencode/step-5-preview-free
🧠 88💻 98
StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window
Context Length1,000,000 tokens
Max Completion65,536 tokens
ModalitiesInput: text, image, video
Output: text
Supported Parameterstools, tool_choice, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Cohere: North Mini Code (free)OpenRouter

ID:  cohere/north-mini-code:free
🧠 80💻 72
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
Context Length256,000 tokens
Max Completion64,000 tokens
ModalitiesInput: text
Output: text
Supported Parametersfrequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, seed, stop, temperature, tool_choice, tools, top_k, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Dots Studio: Dots3-Note Preview (free)OpenRouter

ID:  dots-studio/dots-3-note-preview:free
🧠 96💻 95
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...
Context Length512,000 tokens
Max Completion460,800 tokens
ModalitiesInput: text, image
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, response_format, structured_outputs, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Google: Gemma 4 26B A4B (free)OpenRouter

ID:  google/gemma-4-26b-a4b-it:free
🧠 82💻 86
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Context Length262,144 tokens
Max Completion32,768 tokens
ModalitiesInput: image, text, video
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, response_format, seed, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Google: Gemma 4 31B (free)OpenRouter

ID:  google/gemma-4-31b-it:free
🧠 82💻 86
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Context Length262,144 tokens
Max Completion32,768 tokens
ModalitiesInput: image, text, video
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, response_format, seed, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

LiquidAI: LFM2.5-2.6B (free)OpenRouter

ID:  liquid/lfm-2.5-2.6b:free
🧠 67💻 68
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Context Length65,536 tokens
Max Completion8,192 tokens
ModalitiesInput: text
Output: text
Supported Parametersfrequency_penalty, include_reasoning, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

NVIDIA: Nemotron 3 Nano Omni (free)OpenRouter

ID:  nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
🧠 80💻 77
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
Context Length256,000 tokens
Max Completion65,536 tokens
ModalitiesInput: text, audio, image, video
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, seed, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

NVIDIA: Nemotron 3 Super (free)OpenRouter

ID:  nvidia/nemotron-3-super-120b-a12b:free
🧠 92💻 85
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Context Length262,144 tokens
Max Completion235,929 tokens
ModalitiesInput: text
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

NVIDIA: Nemotron 3 Ultra (free)OpenRouter

ID:  nvidia/nemotron-3-ultra-550b-a55b:free
🧠 88💻 83
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Context Length1,000,000 tokens
Max Completion65,536 tokens
ModalitiesInput: text
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, reasoning_effort, seed, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

NVIDIA: Nemotron 3.5 Content Safety (free)OpenRouter

ID:  nvidia/nemotron-3.5-content-safety:free
🧠 60💻 38
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
Context Length128,000 tokens
Max Completion8,192 tokens
ModalitiesInput: text, image
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, seed, temperature, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

NVIDIA: Nemotron 3.5 Lightning (free)OpenRouter

ID:  nvidia/nemotron-3.5-lightning:free
🧠 88💻 83
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Context Length1,000,000 tokens
Max Completion65,536 tokens
ModalitiesInput: text
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, seed, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

✨ New Free Model Added: NVIDIA: Nemotron 3.5 Super VL (free)OpenRouterNEW

ID:  nvidia/nemotron-3.5-super-vl:free
🧠 96💻 99
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
Context Length1,000,000 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image, video
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Poolside: Laguna S 2.1 (free)OpenRouter⚠️ DEPRECATED · expires 2026-10-31

ID:  poolside/laguna-s-2.1:free
🧠 77💻 71
Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
Context Length262,144 tokens
Max Completion32,768 tokens
ModalitiesInput: text
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, temperature, tool_choice, tools
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Poolside: Laguna XS 2.1 (free)OpenRouter⚠️ DEPRECATED · expires 2026-10-31

ID:  poolside/laguna-xs-2.1:free
🧠 77💻 71
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Context Length262,144 tokens
Max Completion32,768 tokens
ModalitiesInput: text
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, temperature, tool_choice, tools
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Thinking Machines: Inkling Small (free)OpenRouter

ID:  thinkingmachines/inkling-small:free
🧠 95💻 90
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Context Length1,048,576 tokens
Max Completion262,144 tokens
ModalitiesInput: text, image, audio
Output: text
Supported Parametersfrequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, reasoning_effort, seed, stop, temperature, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP15/10/2026 18:43

Thinking Machines: Inkling (free)OpenRouter

ID:  thinkingmachines/inkling:free
🧠 95💻 90
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Context Length1,048,576 tokens
Max Completion262,144 tokens
ModalitiesInput: text, image, audio
Output: text
Supported Parametersfrequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, reasoning_effort, seed, stop, temperature, tools, top_p
Free Models Monitor · Auto Notification

Activity timeline

Activity timeline

15 October 2026
Free Models MonitorAPP2026-10-15 18:13

✨ New Free Model Added: NVIDIA: Nemotron 3.5 Super VL (free)OpenRouterNEW

ID:  nvidia/nemotron-3.5-super-vl:free
🧠 96💻 99
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
Context Length1,000,000 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image, video
Output: text
Supported Parametersinclude_reasoning, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-15 18:13

✨ New Free Model Added: OpenCode: DeepSeek V4.1 Flash FreeOpenCodeNEW

ID:  opencode/deepseek-v4.1-flash-free
🧠 80💻 84
DeepSeek V4.1 Flash model for reasoning and agentic coding
Context Length200,000 tokens
Max Completion32,000 tokens
ModalitiesInput: text, image
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-15 18:13

✨ New Free Model Added: OpenCode: Nemotron 3.5 Super VL FreeOpenCodeNEW

ID:  opencode/nemotron-3.5-super-vl-free
🧠 92💻 89
NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use
Context Length1,048,576 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning
Free Models Monitor · Auto Notification
14 October 2026
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Big PickleOpenCodeNEW

ID:  opencode/big-pickle
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Context Length200,000 tokens
Max Completion32,000 tokens
ModalitiesInput: text
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Cat Jam FreeOpenCodeNEW

ID:  opencode/cat-jam-free
A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.
Context Length262,144 tokens
Max Completion131,072 tokens
ModalitiesInput: text
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: LongCat 2.5 Preview FreeOpenCodeNEW

ID:  opencode/longcat-2.5-preview-free
Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window
Context Length1,000,000 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: MiMo-V2.6-Flash FreeOpenCodeNEW

ID:  opencode/mimo-v2.6-flash-free
MiMo Flash model for multimodal coding agents and long-context automation
Context Length200,000 tokens
Max Completion32,000 tokens
ModalitiesInput: text, image, audio, video
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Muse Spark 1.2 FreeOpenCodeNEW⚠️ DEPRECATED

ID:  opencode/muse-spark-1.2-contributor-free
Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.
Context Length1,048,576 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image, video, pdf, audio
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Muse Spark 1.3 FreeOpenCodeNEW

ID:  opencode/muse-spark-1.3-contributor-free
Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.
Context Length1,048,576 tokens
Max Completion131,072 tokens
ModalitiesInput: text, image, video, pdf, audio
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Nemotron 3.5 Lightning FreeOpenCodeNEW

ID:  opencode/nemotron-3.5-lightning-free
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Context Length262,144 tokens
Max Completion262,144 tokens
ModalitiesInput: text
Output: text
Supported Parameterstools, tool_choice, temperature, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Space Bunny FreeOpenCodeNEW

ID:  opencode/space-bunny-free
Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input
Context Length1,048,576 tokens
Max Completion524,288 tokens
ModalitiesInput: text, image, video
Output: text
Supported Parameterstools, tool_choice, reasoning, include_reasoning
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:34

✨ OpenCode: Step 5 Preview FreeOpenCodeNEW

ID:  opencode/step-5-preview-free
StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window
Context Length1,000,000 tokens
Max Completion65,536 tokens
ModalitiesInput: text, image, video
Output: text
Supported Parameterstools, tool_choice, reasoning, include_reasoning, structured_outputs, response_format
Free Models Monitor · Auto Notification
Free Models MonitorAPP2026-10-14 14:02
Initial import of 14 free models.