Free AI Chat Models (November 2026): 15 Models Compared
All 15 free AI chat models available in November 2026, compared by context window, input types and best use, with links to a detailed page for each.
· 5 min read
Blog category
Specs, limits and how-to guides for the newest free AI chat models, with a comparison roundup.
This category covers the newest AI chat models, starting with those you can use for free. Each model gets its own page with the facts that matter before you use it: who built it, how big it is, how much text it can read and write at once, which kinds of input it accepts, and whether a paid version exists.
We keep the focus on verifiable details taken from public model catalogues and we state the date they were checked. We do not publish made-up benchmark scores. Instead each page lists limits to watch for, privacy cautions about free endpoints, and test prompts so you can judge the model on your own work.
Start with the roundup, which compares all of the free models in one table and explains how to choose between them. Then open the individual pages for the models that fit your task. If terms like mixture-of-experts or context window are new, our AI Fundamentals track explains them from the beginning.
New articles are added regularly, and older ones are revised when the technology or our understanding changes. Check the updated date at the top of each article.
If you are new, start with the oldest or most introductory article and work forward, because later pieces assume the vocabulary of earlier ones. If you already know the basics, scan the titles for the specific problem you are stuck on. Each article ends with questions and answers, and links to related lessons and articles so you can keep going without searching elsewhere. Our glossary explains any unfamiliar term, and our learning tracks offer a structured route when you want one.
All 15 free AI chat models available in November 2026, compared by context window, input types and best use, with links to a detailed page for each.
· 5 min read
Input, output and cached prices for 31 paid AI chat models in November 2026, with the cheapest and priciest, pricing quirks and a cost-estimate guide.
· 6 min read
inclusionAI Ling 3.2 Flash free: hybrid reasoning model, text/image input, 1M context. Specs, limits, test prompts and how to try it.
· 3 min read
Baidu ERNIE 5.5 Flash Preview free: foundation model (preview), text input, 1M context. Specs, limits, test prompts and how to try it.
· 3 min read
Thinking Machines Inkling 2 Small free: open-weight multimodal mixture-of-experts reasoning model, text/image input, 1M context. Specs, limits, test...
· 3 min read
LiquidAI LFM3-1.7B free: compact reasoning text model, text input, 262K context. Specs, limits, test prompts and how to try it.
· 3 min read
Particle AI Particle-1 free: agentic coding model post-trained on DeepSeek V4.1 Flash, text/image input, 1M context. Specs, limits, test prompts and how...
· 3 min read
Recursive Flint free: open-weight mixture-of-experts model, text input, 262K context. Specs, limits, test prompts and how to try it.
· 3 min read
NVIDIA Nemotron 3.5 Super VL free: open multimodal mixture-of-experts model, text/image/video input, 1M context. Specs, limits, test prompts and how to...
· 3 min read
Dots Studio Dots3-Note Preview free: open-weight mixture-of-experts model (preview), text/image input, 512K context. Specs, limits, test prompts and how...
· 3 min read
NVIDIA Nemotron 3.5 Lightning free: open mixture-of-experts model, text input, 1M context. Specs, limits, test prompts and how to try it.
· 3 min read
Cohere North Mini Code free: sparse mixture-of-experts agentic coding model, text input, 256K context. Specs, limits, test prompts and how to try it.
· 3 min read
NVIDIA Nemotron 3 Ultra free: hybrid Transformer-Mamba mixture-of-experts model, text input, 1M context. Specs, limits, test prompts and how to try it.
· 3 min read
NVIDIA Nemotron 3 Nano Omni free: open multimodal reasoning model, text/audio/image/video input, 256K context. Specs, limits, test prompts and how to try it.
· 3 min read
Google Gemma 4 26B A4B free: instruction-tuned mixture-of-experts model, image/text/video input, 262K context. Specs, limits, test prompts and how to try it.
· 3 min read
Google Gemma 4 31B free: dense multimodal instruction-tuned model, image/text/video input, 262K context. Specs, limits, test prompts and how to try it.
· 3 min read
OpenRouter Free Models Router free: router that selects a free model per request, text/image input, 200K context. Specs, limits, test prompts and how to...
· 3 min read
Qwen4 Max: flagship multimodal reasoning model, 1M context, 1.50 in / 4.50 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Google Gemini 4 Hydrogen: high-efficiency workhorse model of the Gemini 4 family, 1M context, 1.50 in / 7.50 out per 1M tokens. Specs, limits and test...
· 3 min read
Google Gemini 4 Carbon: frontier Gemini 4 model for coding, agentic and complex reasoning work, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs...
· 3 min read
Google Gemini 4 Argon: flagship reasoning model, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Baidu ERNIE-Light-DT-1.0: reasoning model based on open-source GLM models with Baidu Sparse Attention, 1M context, 1.13 in / 3.94 out per 1M tokens....
· 3 min read
Nex AGI Nex-N2.6: agentic model built on GLM-5.3-Flash, 262K context, 0.12 in / 0.40 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Anthropic Claude Fable 5.2: most capable Claude model for demanding technical work, 1M context, 8.00 in / 40.00 out per 1M tokens. Specs, limits and test...
· 3 min read
Meta Muse Ember: smallest and most efficient Meta model for repeatable agent work, 1M context, 0.10 in / 0.50 out per 1M tokens. Specs, limits and test...
· 3 min read
KT Mi:dm K 3.0 Pro: mixture-of-experts reasoning model mixing Mamba, MoE and attention layers, 262K context, 0.20 in / 0.80 out per 1M tokens. Specs...
· 3 min read
Tencent Hy4: official release model with strong agentic gains over Hy4 Preview, 1M context, 0.42 in / 1.25 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Ricursive Ripple 65B Preview: 65B model with native tool calling, served in BF16, 1M context, 0.10 in / 0.30 out per 1M tokens. Specs, limits and test...
· 3 min read
Motif Technologies Motif 3: mixture-of-experts multilingual model for English and Korean, 262K context, 0.30 in / 1.20 out per 1M tokens. Specs, limits...
· 3 min read
Z.ai GLM-5.3-FlashX-Legal: legal-domain variant of GLM-5.3-FlashX, 1M context, 0.37 in / 1.25 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
OpenAI GPT-6.1 Terra: mid-tier model in the GPT-6.1 series, 1M context, 1.00 in / 5.00 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
MoonshotAI Kimi K3.1 Pro: flagship open-weight multimodal reasoning model, 1M context, 0.24 in / 8.40 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
MiniMax M3.1 Flash: multimodal model with gains in agentic tasks, coding and cybersecurity, 1M context, 0.15 in / 0.60 out per 1M tokens. Specs, limits...
· 3 min read
DeepSeek V4.1 Flash 1017: sparse mixture-of-experts model (17 October 2026 snapshot), 1M context, 0.15 in / 0.60 out per 1M tokens. Specs, limits and test...
· 3 min read
Reflection Beam 1.0: open-weight sparse mixture-of-experts reasoning model, 1M context, 0.30 in / 1.00 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Meta Muse Spark Open: coding-optimized open-weight model, 1M context, 1.25 in / 4.25 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Meta Muse Wonder: frontier reasoning model for personal and professional agentic tasks, 1M context, 4.00 in / 20.00 out per 1M tokens. Specs, limits and...
· 3 min read
StepFun Step 5 Preview: sparse mixture-of-experts flagship for agentic work, 1M context, 1.00 in / 2.70 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Anthropic Claude Haiku 5.5: small, fast model for high-volume work, 1M context, 0.10 in / 0.50 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Mistral Large 4: frontier multimodal model for reasoning, coding and agentic workloads, 1M context, 0.70 in / 2.10 out per 1M tokens. Specs, limits and...
· 3 min read
inclusionAI Ling 3.1 Flash: hybrid reasoning mixture-of-experts model, 1M context, 0.045 in / 0.14 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
OpenAI GPT-6.1 Sol: upper-mid-tier model in the GPT-6 series, below the flagship GPT-6 Astra, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs, limits...
· 3 min read
Anthropic Claude Sonnet 5.5: Sonnet-class model for well-scoped everyday work, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
Z.ai GLM-5.3-Prime: high-speed variant of GLM-5.3 with 1.5 to 2 times the output throughput, 1M context, 2.80 in / 8.80 out per 1M tokens. Specs, limits...
· 3 min read
Qwen3.8 Max Prime: higher-throughput variant of Qwen3.8 Max, 1M context, 4.00 in / 12.00 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
AionLabs Aion 3.5: multi-model roleplaying and storytelling system built on the GLM family, 262K context, 3.00 in / 6.00 out per 1M tokens. Specs, limits...
· 3 min read
Cohere Command A+: flagship model for enterprise agentic workflows, 192K context, 0.30 in / 1.50 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
OpenAI GPT-6 Luna: fast, cost-efficient model in the GPT-6 series, 1M context, 0.10 in / 0.50 out per 1M tokens. Specs, limits and test prompts.
· 3 min read
We cover the free text-output chat models in the OpenRouter catalogue, including models from NVIDIA, Google, Cohere, Baidu, Liquid AI and others, with a page for each.
No. We do not publish benchmark scores we have not measured. We list verified specifications and give test prompts so you can compare models on your own tasks.
Not by default. Free endpoints may log or reuse prompts, so avoid passwords, keys and confidential data.