
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Free AI Models &amp; Free Tokens - 47 Free LLMs and APIs (2026)</title>
    <link>https://freemodels.net/en/</link>
    <description>Curated 47 free and trial AI models from 9 platforms including OpenRouter, Gemini, Groq, Cloudflare, and OpenCode. Compare free token limits, 1M-context models, coding, and multimodal APIs. Most require no credit card.</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Fri, 20 Nov 2026 16:40:58 +0000</lastBuildDate>
    <atom:link href="https://freemodels.net/en/index.xml" rel="self" type="application/rss&#43;xml" /><item>
      <title>Gemini 3.5 Flash-Lite - Free Low-Latency Multimodal Model, 1M Context</title>
      <link>https://freemodels.net/en/providers/gemini/gemini-3.5-flash-lite/</link>
      <guid>https://freemodels.net/en/providers/gemini/gemini-3.5-flash-lite/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Google&#39;s low-latency, high-throughput multimodal model with a 1M-token context, suited to classification, translation, document parsing, and sub-agent tasks; available on the Gemini free tier.</description>
      <category>gemini</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: gemini-3.5-flash-lite | Input: text, image, video, audio, pdf | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Gemini 3.6 Flash - Free Previous-Generation Multimodal Model, 1M Context</title>
      <link>https://freemodels.net/en/providers/gemini/gemini-3.6-flash/</link>
      <guid>https://freemodels.net/en/providers/gemini/gemini-3.6-flash/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Google&#39;s previous-generation Flash multimodal model balances speed and reasoning, with a 1M-token context, function calling, and structured output; available on the Gemini free tier.</description>
      <category>gemini</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: gemini-3.6-flash | Input: text, image, video, audio, pdf | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Gemini 3.8 Flash - Free Multimodal Gemini Model, 1M Context</title>
      <link>https://freemodels.net/en/providers/gemini/gemini-3.8-flash/</link>
      <guid>https://freemodels.net/en/providers/gemini/gemini-3.8-flash/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Google&#39;s latest Flash multimodal model, built for long-horizon software engineering and autonomous agents, with a 1M-token context and text, image, video, audio, and PDF input; available on the free tier.</description>
      <category>gemini</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: gemini-3.8-flash | Input: text, image, video, audio, pdf | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-4.7-Flash - Free Multilingual Model on Cloudflare, 131K Context</title>
      <link>https://freemodels.net/en/providers/cloudflare/zai-org_glm-4.7-flash/</link>
      <guid>https://freemodels.net/en/providers/cloudflare/zai-org_glm-4.7-flash/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Zhipu&#39;s multilingual text model for chat, instruction following, and multi-turn tool calling. Available on the Cloudflare Workers AI free plan with 131K context and zero data retention.</description>
      <category>cloudflare</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 131K tokens | Model ID: @cf/zai-org/glm-4.7-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GPT-OSS 120B - Free Reasoning Model on Cloudflare, 128K Context</title>
      <link>https://freemodels.net/en/providers/cloudflare/openai_gpt-oss-120b/</link>
      <guid>https://freemodels.net/en/providers/cloudflare/openai_gpt-oss-120b/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>OpenAI&#39;s 120B open-weight reasoning model, available on the Cloudflare Workers AI free plan with 128K context, function calling, and zero data retention.</description>
      <category>cloudflare</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 128K tokens | Model ID: @cf/openai/gpt-oss-120b | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GPT-OSS 120B - Free Reasoning Model on Groq, 131K Context</title>
      <link>https://freemodels.net/en/providers/groq/openai_gpt-oss-120b/</link>
      <guid>https://freemodels.net/en/providers/groq/openai_gpt-oss-120b/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>OpenAI&#39;s 120B open-source reasoning model excels at science, math, coding, and agent tasks; GroqCloud&#39;s free plan offers 131K context at 30 RPM / 1,000 RPD.</description>
      <category>groq</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 131K tokens | Model ID: openai/gpt-oss-120b | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GPT-OSS 20B - Free Lightweight Model on Groq, 131K Context</title>
      <link>https://freemodels.net/en/providers/groq/openai_gpt-oss-20b/</link>
      <guid>https://freemodels.net/en/providers/groq/openai_gpt-oss-20b/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>OpenAI&#39;s 20B open-source reasoning model runs at about 1,000 tokens/s, ideal for high-frequency calls and lightweight agents; GroqCloud&#39;s free plan offers 131K context.</description>
      <category>groq</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 131K tokens | Model ID: openai/gpt-oss-20b | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Qwen 3.8 27B - Free Multimodal Model on Cloudflare, 262K Context</title>
      <link>https://freemodels.net/en/providers/cloudflare/qwen_qwen3.8-27b/</link>
      <guid>https://freemodels.net/en/providers/cloudflare/qwen_qwen3.8-27b/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Alibaba&#39;s 27B multimodal model with text and image input, function calling, and reasoning. Available on the Cloudflare Workers AI free plan with 262K context and zero data retention.</description>
      <category>cloudflare</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 262K tokens | Model ID: @cf/qwen/qwen3.8-27b | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Qwen 3.8 27B - Free Multimodal Model on Groq, 131K Context</title>
      <link>https://freemodels.net/en/providers/groq/qwen_qwen3.8-27b/</link>
      <guid>https://freemodels.net/en/providers/groq/qwen_qwen3.8-27b/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Alibaba&#39;s 27B multimodal model supports image input, reasoning, function calling, and tool use; GroqCloud&#39;s free plan offers 131K context at 30 RPM / 1,000 RPD.</description>
      <category>groq</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 131K tokens | Model ID: qwen/qwen3.8-27b | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Ming Image 0.1 Design (Free) - ZenMux Text-to-Image Design Model</title>
      <link>https://freemodels.net/en/providers/zenmux/inclusionai_ming-image-0.1-design/</link>
      <guid>https://freemodels.net/en/providers/zenmux/inclusionai_ming-image-0.1-design/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>inclusionAI&#39;s text-to-image design model emphasizes text rendering inside images and suits posters, graphic design, and UI mockups, with free $0/$0 access on ZenMux.</description>
      <category>zenmux</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 8K tokens | Model ID: inclusionai/ming-image-0.1-design | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Ming Image 0.1 Design Layer (Free) - ZenMux Image Layering Model</title>
      <link>https://freemodels.net/en/providers/zenmux/inclusionai_ming-image-0.1-design-layer/</link>
      <guid>https://freemodels.net/en/providers/zenmux/inclusionai_ming-image-0.1-design-layer/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>inclusionAI&#39;s image layering model splits flat designs into separate RGBA layers such as background and foreground, with free $0/$0 access on ZenMux.</description>
      <category>zenmux</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 8K tokens | Model ID: inclusionai/ming-image-0.1-design-layer | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>PaddleOCR-VL 1.5 - Free Document Parsing Model on SiliconFlow, 16K Context</title>
      <link>https://freemodels.net/en/providers/siliconflow/paddlepaddle_paddleocr-vl-1.5_free/</link>
      <guid>https://freemodels.net/en/providers/siliconflow/paddlepaddle_paddleocr-vl-1.5_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Baidu&#39;s 0.9B multimodal document parsing model, with 94.5% accuracy on OmniDocBench v1.5, support for 111 languages, and seal and cross-page table recognition. Free on SiliconFlow.</description>
      <category>siliconflow</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 16K tokens | Model ID: PaddlePaddle/PaddleOCR-VL-1.5 | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Recursive Flint 1.0 - Free Coding Model on OpenRouter, 262K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/recursive_flint-v1.0free_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/recursive_flint-v1.0free_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Recursive&#39;s 40B total / 2.5B active MoE model built for coding agents, with 262K context and free tokens on OpenRouter.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 262K tokens | Model ID: recursive/flint-v1.0:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Xing4.0 29B - Free MoE Model on SiliconFlow, 256K Context</title>
      <link>https://freemodels.net/en/providers/siliconflow/xingchenagi_xing4.0-29b_free/</link>
      <guid>https://freemodels.net/en/providers/siliconflow/xingchenagi_xing4.0-29b_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>TeleAI&#39;s open-source 29B MoE model with 4B active parameters per token, native 256K context, and a focus on agentic coding and long-horizon tasks. Free on SiliconFlow.</description>
      <category>siliconflow</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 256K tokens | Model ID: XingChenAGI/Xing4.0-29B | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Agnes 2.5 Flash (Free) - ZenMux Multimodal Reasoning Model, 512K Context</title>
      <link>https://freemodels.net/en/providers/zenmux/sapiens-ai_agnes-2.5-flash/</link>
      <guid>https://freemodels.net/en/providers/zenmux/sapiens-ai_agnes-2.5-flash/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Sapiens AI&#39;s multimodal reasoning model on ZenMux supports image input and a 524K ultra-long context, ideal for visual Q&amp;A and document understanding, at $0/$0.</description>
      <category>zenmux</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 524K tokens | Model ID: sapiens-ai/agnes-2.5-flash | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Dots3 Note Preview (Free) - ZenMux Omni-Modal Preview Model, 384K Context</title>
      <link>https://freemodels.net/en/providers/zenmux/dots-studio_dots3-note-prev/</link>
      <guid>https://freemodels.net/en/providers/zenmux/dots-studio_dots3-note-prev/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Dots Studio&#39;s omni-modal preview model on ZenMux accepts text, image, video, and audio input with a 393K context and reasoning, free of charge.</description>
      <category>zenmux</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 393K tokens | Model ID: dots-studio/dots3-note-prev | Input: text, image, video, audio | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-4.6V-Flash - Free Zhipu Vision Model with 128K Context</title>
      <link>https://freemodels.net/en/providers/z-ai/glm-4.6v-flash_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/glm-4.6v-flash_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Zhipu&#39;s free visual reasoning model with a 128K context window, supporting image understanding, tool calling, and multi-step analysis for image Q&amp;A and document parsing; offered free at $0 on the Z.Ai platform.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 128K tokens | Model ID: z-ai/glm-4.6v-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-4.7-Flash - Free Zhipu Model with 200K Context</title>
      <link>https://freemodels.net/en/providers/z-ai/glm-4.7-flash_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/glm-4.7-flash_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>The affordable version of Zhipu AI&#39;s latest base model with a 200K context window, ideal for long-document processing, Chinese conversation, and agent tasks; offered free at $0 on the Z.Ai platform.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 200K tokens | Model ID: z-ai/glm-4.7-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Google Lyria 3 Clip - Free Music Clip Generation on OpenRouter</title>
      <link>https://freemodels.net/en/providers/openrouter/google_lyria-3-clip-preview_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/google_lyria-3-clip-preview_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>Google&#39;s music clip generation model produces 30-second audio, loops, and previews from text or image input; free to call on OpenRouter at $0.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: google/lyria-3-clip-preview | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Nemotron 3.5 Super VL - Free Omni-Modal Model on OpenRouter, 1M Context</title>
      <link>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3.5-super-vlfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3.5-super-vlfree_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>NVIDIA&#39;s 120B total / 12B active omni-modal MoE model supports text, image, and video input with a 1M context; available free on OpenRouter.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: nvidia/nemotron-3.5-super-vl:free | Input: text, image, video | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>OpenRouter Free - Auto-Routed Free Models, 200K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/openrouter_free_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/openrouter_free_free/</guid>
      <pubDate>Fri, 06 Nov 2026 00:00:00 +0800</pubDate>
      <description>OpenRouter&#39;s auto-routing service randomly selects from the platform&#39;s free models, with 200K context; ideal for quick testing and prototyping at $0 with no credit card required.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 200K tokens | Model ID: openrouter/free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>ERNIE 5.5 Flash Preview - Free 1M Context Model on OpenRouter</title>
      <link>https://freemodels.net/en/providers/openrouter/baidu_ernie-5.5-flash-previewfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/baidu_ernie-5.5-flash-previewfree_free/</guid>
      <pubDate>Wed, 11 Nov 2026 00:00:00 +0800</pubDate>
      <description>Baidu&#39;s ERNIE 5.5 Flash Preview free model has 280B parameters and 1M context, focused on coding, agents, and deep research.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: baidu/ernie-5.5-flash-preview:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>LFM3 1.7B - Free Lightweight Model on OpenRouter, 262K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/liquid_lfm-3-1.7bfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/liquid_lfm-3-1.7bfree_free/</guid>
      <pubDate>Wed, 11 Nov 2026 00:00:00 +0800</pubDate>
      <description>Liquid AI&#39;s compact 1.7B text model with 262K context, supporting tool calling, structured output, and reasoning; available free on OpenRouter.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 262K tokens | Model ID: liquid/lfm-3-1.7b:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>DeepSeek V4.1 Flash Free - Free Model on OpenCode, 200K Context</title>
      <link>https://freemodels.net/en/providers/opencode/deepseek-v4.1-flash-free/</link>
      <guid>https://freemodels.net/en/providers/opencode/deepseek-v4.1-flash-free/</guid>
      <pubDate>Fri, 13 Nov 2026 00:00:00 +0800</pubDate>
      <description>DeepSeek V4.1 Flash free edition with 200K context, 32K output, text and image input, tool calling, and reasoning; available only in the OpenCode client.</description>
      <category>opencode</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 200K tokens | Model ID: opencode/deepseek-v4.1-flash-free | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-5.3-Flash Free - Free Multimodal Model on OpenCode, 200K Context</title>
      <link>https://freemodels.net/en/providers/opencode/glm-5.3-flash-free/</link>
      <guid>https://freemodels.net/en/providers/opencode/glm-5.3-flash-free/</guid>
      <pubDate>Fri, 13 Nov 2026 00:00:00 +0800</pubDate>
      <description>Zhipu AI&#39;s GLM-5.3-Flash free edition with 200K context, 32K output, text, image, and video input, and reasoning; available only in the OpenCode client.</description>
      <category>opencode</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 200K tokens | Model ID: opencode/glm-5.3-flash-free | Input: text, image, video | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>LongCat 2.5 Free - Free 1M Context Model on OpenCode, China-Hosted</title>
      <link>https://freemodels.net/en/providers/opencode/longcat-2.5-free/</link>
      <guid>https://freemodels.net/en/providers/opencode/longcat-2.5-free/</guid>
      <pubDate>Fri, 13 Nov 2026 00:00:00 +0800</pubDate>
      <description>Meituan&#39;s LongCat 2.5 free edition with 1M context, 262K output, text and image input, and reasoning; hosted in China and available only in the OpenCode client.</description>
      <category>opencode</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: opencode/longcat-2.5-free | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>MiniMax M3.1 Flash Free - Free 1M Context Model on OpenCode</title>
      <link>https://freemodels.net/en/providers/opencode/minimax-m3.1-flash-free/</link>
      <guid>https://freemodels.net/en/providers/opencode/minimax-m3.1-flash-free/</guid>
      <pubDate>Fri, 13 Nov 2026 00:00:00 +0800</pubDate>
      <description>MiniMax M3.1 Flash free edition with 1M context, 512K output, text, image, and video input, and adjustable reasoning depth; available only in the OpenCode client.</description>
      <category>opencode</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: opencode/minimax-m3.1-flash-free | Input: text, image, video | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GPT-OSS 120B - Cerebras Free Trial, 65K Context</title>
      <link>https://freemodels.net/en/providers/cerebras/gpt-oss-120b_free/</link>
      <guid>https://freemodels.net/en/providers/cerebras/gpt-oss-120b_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>GPT-OSS 120B is OpenAI&#39;s open-weight reasoning model for science, math, coding, document Q&amp;A and agent tasks, with reasoning effort control, tool calling and structured output. Cerebras serves it at ~3,000 tokens/s with a $5 credit valid for 30 days.</description>
      <category>cerebras</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 65K tokens | Model ID: gpt-oss-120b | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Hunyuan-MT-7B - Free Translation Model on SiliconFlow, 33K Context</title>
      <link>https://freemodels.net/en/providers/siliconflow/tencent_hunyuan-mt-7b_free/</link>
      <guid>https://freemodels.net/en/providers/siliconflow/tencent_hunyuan-mt-7b_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>Hunyuan-MT-7B is Tencent Hunyuan&#39;s lightweight 7B translation model, supporting 33 languages including 5 minority languages spoken in China. It ranked first in 30 of 31 language directions at WMT25. Free on SiliconFlow.</description>
      <category>siliconflow</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 33K tokens | Model ID: tencent/Hunyuan-MT-7B | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Qwen 3.8 27B - Cerebras Free Trial Multimodal Model, 64K Context</title>
      <link>https://freemodels.net/en/providers/cerebras/qwen-3.8-27b_free/</link>
      <guid>https://freemodels.net/en/providers/cerebras/qwen-3.8-27b_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>Qwen 3.8 27B is Alibaba&#39;s 27B dense multimodal model with text and PNG/JPEG image input, 64K context, configurable reasoning effort, tool calling and structured output for agentic coding and long-horizon workflows; callable with Cerebras&#39; $5 trial credit.</description>
      <category>cerebras</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 64K tokens | Model ID: qwen-3.8-27b | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>CogVideoX-Flash - Free Zhipu AI Video Generation Model</title>
      <link>https://freemodels.net/en/providers/z-ai/cogvideox-flash_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/cogvideox-flash_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>CogVideoX-Flash is Zhipu&#39;s free video generation model supporting 4K quality, 60fps frame rates, 10-second duration extension, and immersive AI audio for short videos, ads, product demos, and creative animation at $0 on Z.Ai.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: — tokens | Model ID: z-ai/cogvideox-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>CogView-3-Flash - Free Zhipu AI Image Generation Model</title>
      <link>https://freemodels.net/en/providers/z-ai/cogview-3-flash_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/cogview-3-flash_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>CogView-3-Flash is Zhipu&#39;s free text-to-image model with Chinese prompt support and multi-resolution output, offering rich creative styles and fast generation for posters, illustrations, e-commerce assets, and social media visuals at $0 on Z.Ai.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: — tokens | Model ID: z-ai/cogview-3-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Gemma 4 26B A4B - Free MoE Model on OpenRouter, 262K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/google_gemma-4-26b-a4b-itfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/google_gemma-4-26b-a4b-itfree_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>Gemma 4 26B A4B is Google DeepMind&#39;s multimodal MoE model with 25.2B total parameters and only 3.8B active, offering a 262K context, thinking mode, and near-31B quality at efficient inference cost; free on OpenRouter at $0.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 262K tokens | Model ID: google/gemma-4-26b-a4b-it:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Gemma 4 31B - Free Multimodal Model on OpenRouter, 262K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/google_gemma-4-31b-itfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/google_gemma-4-31b-itfree_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>Gemma 4 31B is Google DeepMind&#39;s 30.7B dense multimodal model with text and image input, a 262K context window, and configurable thinking/reasoning modes for visual Q&amp;A, code generation, and complex reasoning; free on OpenRouter at $0.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 262K tokens | Model ID: google/gemma-4-31b-it:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM 4.6V Flash (Free) - ZenMux Vision Model, 200K Context</title>
      <link>https://freemodels.net/en/providers/zenmux/z-ai_glm-4.6v-flash-free/</link>
      <guid>https://freemodels.net/en/providers/zenmux/z-ai_glm-4.6v-flash-free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>GLM 4.6V Flash is Zhipu&#39;s multimodal vision model. The ZenMux Free version supports text, image, and video input with a 200K context and reasoning for visual Q&amp;A and document parsing at $0/$0.</description>
      <category>zenmux</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 200K tokens | Model ID: z-ai/glm-4.6v-flash-free | Input: text, image, video | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM 4.7 Flash (Free) - ZenMux Reasoning Model, 200K Context</title>
      <link>https://freemodels.net/en/providers/zenmux/z-ai_glm-4.7-flash-free/</link>
      <guid>https://freemodels.net/en/providers/zenmux/z-ai_glm-4.7-flash-free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>GLM 4.7 Flash is Zhipu&#39;s lightweight Flash-series model. The ZenMux Free version offers the full 200K context and reasoning for long documents, Chinese dialogue, and agent tasks at $0/$0.</description>
      <category>zenmux</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 200K tokens | Model ID: z-ai/glm-4.7-flash-free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-4-Flash-250414 - Free Zhipu Long-Context Model, 128K</title>
      <link>https://freemodels.net/en/providers/z-ai/glm-4-flash-250414_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/glm-4-flash-250414_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>GLM-4-Flash-250414 is Zhipu&#39;s free long-context model with a 128K context window and 16K output, supporting multilingual text, external tool calling, and ultra-long document processing for summarization, translation, knowledge-base Q&amp;A, and batch content generation.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 128K tokens | Model ID: z-ai/glm-4-flash-250414 | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-4.1V-Thinking-Flash - Free Zhipu Visual Reasoning Model, 64K</title>
      <link>https://freemodels.net/en/providers/z-ai/glm-4.1v-thinking-flash_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/glm-4.1v-thinking-flash_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>GLM-4.1V-Thinking-Flash is Zhipu&#39;s free visual reasoning model with a 64K context window and 16K output, supporting complex scene understanding, chart interpretation, and multi-step analysis for image Q&amp;A, document OCR, and visual agents at $0 on Z.Ai.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 64K tokens | Model ID: z-ai/glm-4.1v-thinking-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>GLM-4V-Flash - Free Zhipu Image Understanding Model, 16K Context</title>
      <link>https://freemodels.net/en/providers/z-ai/glm-4v-flash_free/</link>
      <guid>https://freemodels.net/en/providers/z-ai/glm-4v-flash_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>GLM-4V-Flash is Zhipu&#39;s free image understanding model with a 16K context window and 1K output, supporting multilingual image Q&amp;A, image description, OCR, and visual content moderation for e-commerce recognition, document parsing, and customer service at $0 on Z.Ai.</description>
      <category>z-ai</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 16K tokens | Model ID: z-ai/glm-4v-flash | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Google Lyria 3 Pro - Free Music Generation Model on OpenRouter</title>
      <link>https://freemodels.net/en/providers/openrouter/google_lyria-3-pro-preview_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/google_lyria-3-pro-preview_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>Google Lyria 3 Pro is a preview music generation model that creates full 48kHz stereo songs from text prompts or images, with verse/chorus structure, sung vocals, timed lyrics, and instrumental arrangement; free at $0 on OpenRouter, though the preview may become paid.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: google/lyria-3-pro-preview | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Nemotron 3 Nano Omni - Free Omni-Modal Model on OpenRouter, 256K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3-nano-omni-30b-a3b-reasoningfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3-nano-omni-30b-a3b-reasoningfree_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>NVIDIA Nemotron 3 Nano Omni is a 30B-A3B omni-modal model supporting text, image, and video input with a 256K context, suited to multimodal retrieval, video understanding, and agent perception tasks; free on OpenRouter at $0.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 256K tokens | Model ID: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Nemotron 3 Ultra 550B - Free Frontier Model on OpenRouter, 1M Context</title>
      <link>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3-ultra-550b-a55bfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3-ultra-550b-a55bfree_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>NVIDIA Nemotron 3 Ultra 550B is a reasoning model with 550B total and 55B active parameters built on a Transformer-Mamba architecture, supporting a 1M context for complex reasoning and long documents; free on OpenRouter at $0.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: nvidia/nemotron-3-ultra-550b-a55b:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Nemotron 3.5 Lightning - Free Fast Model on OpenRouter, 1M Context</title>
      <link>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3.5-lightningfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/nvidia_nemotron-3.5-lightningfree_free/</guid>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0800</pubDate>
      <description>NVIDIA Nemotron 3.5 Lightning is an open MoE fast reasoning model with 30B total and 3B active parameters, optimized for high-throughput agents and specialized tasks, with a 1M context and 64K output; free on OpenRouter at $0.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: nvidia/nemotron-3.5-lightning:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Gemini 4 Hydrogen - Free Flagship Gemini Model, 1M Context</title>
      <link>https://freemodels.net/en/providers/gemini/gemini-4-hydrogen/</link>
      <guid>https://freemodels.net/en/providers/gemini/gemini-4-hydrogen/</guid>
      <pubDate>Sun, 15 Nov 2026 00:00:00 +0800</pubDate>
      <description>Gemini 4 Hydrogen is Google&#39;s free-tier flagship model with a unified 1M-token context, 65K default output (up to 1M with long decode), and text, image, video, audio, and PDF input; free-tier calls cost $0.</description>
      <category>gemini</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: gemini-4-hydrogen | Input: text, image, video, audio, pdf | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Ling 3.2 Flash - Free Multimodal Reasoning Model on OpenRouter, 1M Context</title>
      <link>https://freemodels.net/en/providers/openrouter/inclusionai_ling-3.2-flashfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/inclusionai_ling-3.2-flashfree_free/</guid>
      <pubDate>Sun, 15 Nov 2026 00:00:00 +0800</pubDate>
      <description>Ling 3.2 Flash is inclusionAI&#39;s hybrid reasoning model with text and image input, 1M context, 262K output, and up to 200 images per request; available for $0 on OpenRouter.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: inclusionai/ling-3.2-flash:free | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Particle-1 - Free Agentic Coding Model on OpenRouter, 1M Context</title>
      <link>https://freemodels.net/en/providers/openrouter/particle-ai_particle-1free_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/particle-ai_particle-1free_free/</guid>
      <pubDate>Sun, 15 Nov 2026 00:00:00 +0800</pubDate>
      <description>Particle-1 is Particle AI&#39;s agentic coding model, post-trained on DeepSeek V4.1 Flash, with 1M context, 131K output, and image input; available for $0 on OpenRouter.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 1M tokens | Model ID: particle-ai/particle-1:free | Input: text, image | Price: $0 / $0]]></content:encoded>
    </item><item>
      <title>Dots3 Note Preview - Free MoE Model on OpenRouter, 512K Context</title>
      <link>https://freemodels.net/en/providers/openrouter/dots-studio_dots-3-note-previewfree_free/</link>
      <guid>https://freemodels.net/en/providers/openrouter/dots-studio_dots-3-note-previewfree_free/</guid>
      <pubDate>Sat, 21 Nov 2026 00:00:00 +0800</pubDate>
      <description>Dots3-Note Preview is Dots Studio&#39;s MoE model with 280B total and 16B active parameters, text and image input, and 512K context for long documents and visual agents; $0 on OpenRouter.</description>
      <category>openrouter</category><content:encoded xmlns:content="http://purl.org/rss/1.0/modules/content/"><![CDATA[Context: 512K tokens | Model ID: dots-studio/dots-3-note-preview:free | Input: text | Price: $0 / $0]]></content:encoded>
    </item>
  </channel>
</rss>
