2026-06-23T10:35:00Z https://njump.cloud.vinney.xyz nanogpt https://njump.cloud.vinney.xyz/npub1v2fdmse57a5jddq7aenmlcuj97n6867fm55kktp6uq5lt6m409fsle3fn9 https://pbs.twimg.com/profile_images/1929504325727920128/U7GrZyCS_400x400.jpg https://pbs.twimg.com/profile_images/1929504325727920128/U7GrZyCS_400x400.jpg https://njump.cloud.vinney.xyz/nevent1qqsvgh38pu6e3l57fl3svz4kx7rs4f8xln44xvdk8qj4050mxx2neqqzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xsmg4jk Compare providers before choosing one.<br/><br/>NanoGPT model pages now show how each provider compares on price, response latency and output speed, plus capabilities, limits and an hour-by-hour reliability grid.<br/><br/><a href="https://nano-gpt.com/models">https://nano-gpt.com/models</a> 2026-10-15T09:01:33Z https://njump.cloud.vinney.xyz/nevent1qqstrznz7l8gs3hhd48zjh7tlz43csdtt5dchz70ggaanak9t0qf9cczyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x32zdka Clef Omni now accepts audio in NanoGPT&#39;s Decisions API.<br/><br/>Send one 0.1-10 second PCM16 WAV clip, optionally with text or images, for typed decisions and probabilities. Audio uses the native Decisions/System One endpoints.<br/><br/><a href="https://nano-gpt.com/models/decisions/cloudflare/clef-omni">https://nano-gpt.com/models/decisions/cloudflare/clef-omni</a> 2026-10-15T04:46:37Z https://njump.cloud.vinney.xyz/nevent1qqs8a8lp256w0d9p3stkyth76rdmxaypzfpeg55z8dsjyslglv52cegzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xq5yw8g Liquid AI&#39;s LFM2.5 24B A2B is now on NanoGPT.<br/><br/>A text reasoning model with 24B total and 2.45B active parameters. It thinks before answering, supports tool calling and structured output, and has a 128K-token context.<br/><br/><a href="https://nano-gpt.com/conversation?model=liquid%2Flfm-2.5-24b-a2b">https://nano-gpt.com/conversation?model=liquid%2Flfm-2.5-24b-a2b</a> 2026-10-15T00:42:54Z https://njump.cloud.vinney.xyz/nevent1qqswdnz5wm8yf46rwfrgkcrqhzxtdt0kuedcfvwgwa69p2cg7sh6z8gzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xxmjnm7 Gemini 4 Argon now also has Flex and Priority tiers on NanoGPT.<br/><br/>Flex is 50% cheaper than Standard when you can wait. Priority costs 80% more for higher-priority processing. Choose in model settings or set service_tier in the API.<br/><br/><a href="https://nano-gpt.com/conversation?model=google%2Fgemini-4-argon">https://nano-gpt.com/conversation?model=google%2Fgemini-4-argon</a> 2026-10-14T20:58:29Z https://njump.cloud.vinney.xyz/nevent1qqsvj9dn276jf9m6lzppwp36ym0lntz5064vv7elrqwuddmkxa2e2dqzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xxcae7f Gemini 4 Argon is now on NanoGPT.<br/><br/>Google&#39;s flagship reasoning model for coding, science and multi-step agents. Work with text, images, audio, video and PDFs, with tool calling, structured output and a 1M-token context.<br/><br/><a href="https://nano-gpt.com/conversation?model=google%2Fgemini-4-argon">https://nano-gpt.com/conversation?model=google%2Fgemini-4-argon</a> 2026-10-14T16:39:50Z https://njump.cloud.vinney.xyz/nevent1qqswawm4ekq3nxvtl6dg90d7emckez6q4wjur9ld6twkeg7l2zr98nszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x424tey A new option for creative writing and roleplay: TheDrummer&#39;s Skyfall 31B v4.2.<br/><br/>Now on NanoGPT with a 16K context window, included in the subscription at the standard 1x rate.<br/><br/><a href="https://nano-gpt.com/conversation?model=TheDrummer%2FSkyfall-31B-v4.2">https://nano-gpt.com/conversation?model=TheDrummer%2FSkyfall-31B-v4.2</a> 2026-10-14T02:38:18Z https://njump.cloud.vinney.xyz/nevent1qqs20s8vlcyanh0376a2kfuvw8h4j7mur58sh07df3353k58vdjcsgszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x0t04mx Kandinsky 6 Lite and Pro are now on NanoGPT.<br/><br/>Create 5-second videos with synchronized sound from a prompt or starting image. Both support English and Russian prompts. Current output is 480p.<br/><br/>Lite: <a href="https://nano-gpt.com/media?mode=video&amp;model=kandinsky6-lite">https://nano-gpt.com/media?mode=video&amp;model=kandinsky6-lite</a><br/>Pro: <a href="https://nano-gpt.com/media?mode=video&amp;model=kandinsky6-pro">https://nano-gpt.com/media?mode=video&amp;model=kandinsky6-pro</a> 2026-10-13T22:37:45Z https://njump.cloud.vinney.xyz/nevent1qqszmp2nu2levq3swq7lj0ugnzr4aupjuse2wpfxzwf0k0ucmqz032czyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xthvc0g Route a request, pick a category or score text without generating a chat reply.<br/><br/>Jared Palmer&#39;s Kev 4B is now on NanoGPT&#39;s Decisions API, returning typed answers and probabilities in one forward pass.<br/><br/><a href="https://nano-gpt.com/models/decisions/jaredpalmer/kev-4b">https://nano-gpt.com/models/decisions/jaredpalmer/kev-4b</a> 2026-10-13T18:34:44Z https://njump.cloud.vinney.xyz/nevent1qqstr88wl5yhzc2sv9xrk8g7necf7xd966y9tfedyjga58uwnnjf73czyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xhqlr4l Tell the cutout what to keep.<br/><br/>Bria Guided Background Removal is now on NanoGPT. Keep the person and the plant, isolate one object, or remove an unwanted item from the cutout. Retained pixels stay unchanged.<br/><br/><a href="https://nano-gpt.com/media?mode=image&amp;model=bria%2Fremove-background-guided">https://nano-gpt.com/media?mode=image&amp;model=bria%2Fremove-background-guided</a> 2026-10-13T14:35:55Z https://njump.cloud.vinney.xyz/nevent1qqs2sncusj5rqz5esydz3atcc8a0a0ucrjnmyppn83wt22ykk32ydfgzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xwdmj79 Meta&#39;s Muse Wonder is live on NanoGPT.<br/><br/>Work with text, images, audio, video and PDFs in a 1M-token context. Reasoning, tool calling and structured output are supported.<br/><br/><a href="https://nano-gpt.com/conversation?model=meta%2Fmuse-wonder">https://nano-gpt.com/conversation?model=meta%2Fmuse-wonder</a> 2026-10-13T08:29:51Z https://njump.cloud.vinney.xyz/nevent1qqsgpyyw3rpnku09es7n5v38uc4gpkfgsvwenq6y7l0c34kheqmfggszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x3nmhmf Native computer use is now supported in NanoGPT&#39;s Responses API with GPT-6 Astra and GPT-6.1 Sol.<br/><br/>Your app executes the model&#39;s computer actions and sends screenshots back.<br/><br/>Currently supported through the native OpenAI route.<br/><br/><a href="https://docs.nano-gpt.com/api-reference/endpoint/responses">https://docs.nano-gpt.com/api-reference/endpoint/responses</a> 2026-10-12T10:00:38Z https://njump.cloud.vinney.xyz/nevent1qqs08cyv0325susvtsd222eufkwh2ua235arym3dgrklmp9aahkc6dgzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x8t20lg New in NanoGPT: &#34;Ask me questions.&#34;<br/><br/>Enable it in Tools. When a model needs a decision, it can show up to three questions. Choose suggested answers, type your own, or leave it &#34;Up to you.&#34;<br/><br/><a href="https://nano-gpt.com/chat">https://nano-gpt.com/chat</a> 2026-10-12T05:58:34Z https://njump.cloud.vinney.xyz/nevent1qqsrhrhnphmwn9zf4wkyxknvgcn9zhqqmmamq3dqf88fx0wszvj8hlszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x4ll4n3 GPT-6.1 Sol now supports Ultrafast on NanoGPT.<br/><br/>Select it in chat settings or use service_tier: &#34;ultrafast&#34; in API requests for faster token generation.<br/><br/>Ultrafast costs 6x Standard pricing.<br/><br/><a href="https://nano-gpt.com/conversation?model=openai%2Fgpt-6.1-sol">https://nano-gpt.com/conversation?model=openai%2Fgpt-6.1-sol</a> 2026-10-11T13:50:13Z https://njump.cloud.vinney.xyz/nevent1qqsfnjaumer4sflxs082sauw6frd2pyuf47zfyua8upc06drw3vvn6qzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xj062qa NanoGPT&#39;s Decisions API now accepts images.<br/><br/>Classify visual content, score it, or ask yes/no questions with structured answers and probabilities.<br/><br/>Available with PPLX Decider v1.1, Clef and Clef Flash. Up to four images, each up to 512x512.<br/><br/><a href="https://nano-gpt.com/openapi.json">https://nano-gpt.com/openapi.json</a> 2026-10-11T11:02:55Z https://njump.cloud.vinney.xyz/nevent1qqszfrwfupadey9e7ne7de5a7k6uvnxze6yludfyxn3ewh4q580kxmszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xzur5dn Run Claude jobs at 50% lower token rates with Anthropic Message Batches on NanoGPT.<br/><br/>Use the official Anthropic SDK with your NanoGPT key. Submit up to 100,000 requests for one supported Claude model, then download the results when they&#39;re ready.<br/><br/><a href="https://docs.nano-gpt.com/api-reference/endpoint/batches#anthropic-message-batches">https://docs.nano-gpt.com/api-reference/endpoint/batches#anthropic-message-batches</a> 2026-10-11T06:02:15Z https://njump.cloud.vinney.xyz/nevent1qqsphltjmfvt8frzn3qls06u87xlshxehqfppyl5g9jcefsxcghj7cczyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xtxhllf ACE-Step 1.5 XL Turbo is now on NanoGPT.<br/><br/>Generate songs from 30 seconds to 5 minutes, with custom lyrics or instrumentals. You can also turn a reference track into a cover, replace a section, or extend it.<br/><br/><a href="https://nano-gpt.com/media?mode=audio&amp;audioMode=tts&amp;model=ACE-Step-v1.5-XL-Turbo">https://nano-gpt.com/media?mode=audio&amp;audioMode=tts&amp;model=ACE-Step-v1.5-XL-Turbo</a> 2026-10-10T23:33:27Z https://njump.cloud.vinney.xyz/nevent1qqs9e4ldrhnnm2779yqarz0gkpnk4cpr3ggs99svjdjs035xq9qepfqzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xg9j8ek Qwen Image 2.1 Turbo is now on NanoGPT.<br/><br/>Generate and edit images with Chinese and English text, combine up to three reference images, and choose 1K or 2K output.<br/><br/>$0.0272 per image at either resolution.<br/><br/><a href="https://nano-gpt.com/media?mode=image&amp;model=qwen-image-2.1-turbo">https://nano-gpt.com/media?mode=image&amp;model=qwen-image-2.1-turbo</a> 2026-10-10T19:31:47Z https://njump.cloud.vinney.xyz/nevent1qqsz3yskxv2x6yvmx3r4sf7ez480gcnym69kahvfz9mcwcnn56lqljqzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xurcz74 ElevenLabs Audio Isolation is now on NanoGPT.<br/><br/>Remove background noise from speech to clean up interviews, podcasts and voice recordings.<br/><br/><a href="https://nano-gpt.com/media?mode=audio&amp;audioMode=tts&amp;model=elevenlabs%2Faudio-isolation">https://nano-gpt.com/media?mode=audio&amp;audioMode=tts&amp;model=elevenlabs%2Faudio-isolation</a> 2026-10-09T15:13:36Z https://njump.cloud.vinney.xyz/nevent1qqsxjuhljcfd09p3keg8ftgzuy3q3t44a74cwra089rsvuwrgl70z4gzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x5gw2qv Apex Flash 1 and Apex Flash 1 Abliterated are now on NanoGPT.<br/><br/>GLM 5.3 Flash cybersecurity finetunes for code investigation and tool use. Both included in the subscription.<br/><br/>Abliterated is experimental, with modified refusal behavior.<br/><br/><a href="https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash-apex">https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash-apex</a> 2026-10-06T15:11:45Z https://njump.cloud.vinney.xyz/nevent1qqs04ed6xt53w76akpjh5nvz5szz54theuwzrfxhj2w0vy7vl6ktj3qzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x2mqvfq Eight new Qwen 3.8 27B finetunes are now on NanoGPT: Antislop, DarkIdol, Fimi, Kimiko, Kiwen, Novelist, Swift and Synthia.<br/><br/>All have 262K context and are included in the subscription at the standard 1x usage rate.<br/><br/><a href="https://nano-gpt.com/models">https://nano-gpt.com/models</a> 2026-10-06T10:35:42Z https://njump.cloud.vinney.xyz/nevent1qqsf2ssh84qlewl6dt5npeqq6wxqgyy68ydjvkrm6e69qplzxt8hwxczyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xan0f4c A product page in. Name, price and location out as JSON.<br/><br/>Schematron V2 Small and Turbo are now on the NanoGPT API. Send HTML and a JSON schema defining the fields you need.<br/><br/>Small focuses on extraction accuracy; Turbo on speed and cost.<br/><br/>API-only:<br/><a href="https://nano-gpt.com/api">https://nano-gpt.com/api</a> 2026-09-14T12:25:27Z https://njump.cloud.vinney.xyz/nevent1qqstweypc9efe3sxgakwysuawjmnluh3h3pa9ch5ayx7z96jt63e9tszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x8d09sa A still product shot becomes a moving close-up.<br/><br/>P-Video 2 is now on NanoGPT: turn text or images into short videos, with generated audio and a lower-cost Draft mode for previews.<br/><br/>Try it:<br/><a href="https://nano-gpt.com/media?mode=video&amp;model=pruna-ai%2Fp-video-2%2Fimage-to-video">https://nano-gpt.com/media?mode=video&amp;model=pruna-ai%2Fp-video-2%2Fimage-to-video</a> 2026-09-14T02:22:50Z https://njump.cloud.vinney.xyz/nevent1qqs8xpakuejhrnahmn4nncm523tdpnelg0nvnmpr6vsp8qagzwqma5gzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xwchmjv Ling 3.0 Flash VL is now on NanoGPT and included in your subscription.<br/><br/>Analyze images, charts, documents and videos with reasoning and tool calling.<br/><br/>256K context, with 5.5B active parameters.<br/><br/><a href="https://nano-gpt.com/conversation?model=inclusionai%2Fling-3.0-flash-vl">https://nano-gpt.com/conversation?model=inclusionai%2Fling-3.0-flash-vl</a> 2026-09-13T04:12:06Z https://njump.cloud.vinney.xyz/nevent1qqsxvk240036n3durfufzz2xvqpg5qzkewksa7y00hqacrfw2ea3s3gzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xmk8ysy Private Mode on NanoGPT now supports PDFs.<br/><br/>Ask questions, summarize documents and extract information. Enable Private Mode before attaching your PDF. Files are encrypted in your browser and processed inside a secure enclave.<br/><br/>Up to 3 MiB per PDF. Processing is charged separately from model usage.<br/><br/><a href="https://nano-gpt.com/chat">https://nano-gpt.com/chat</a> 2026-09-13T00:11:42Z https://njump.cloud.vinney.xyz/nevent1qqs85yf54gczanylgdh5s6dg6sau079jnuwkan4tfwekx4jf8r2u2wqzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xpmqeg5 BiRefNet V2 and SAM 3 are now on NanoGPT.<br/><br/>Remove backgrounds with BiRefNet, or describe the person, object or region you want SAM 3 to isolate. Create cutouts and masks for further editing.<br/><br/>BiRefNet V2:<br/><a href="https://nano-gpt.com/media?mode=image&amp;model=birefnet%2Fv2">https://nano-gpt.com/media?mode=image&amp;model=birefnet%2Fv2</a><br/><br/>SAM 3:<br/><a href="https://nano-gpt.com/media?mode=image&amp;model=sam3-image">https://nano-gpt.com/media?mode=image&amp;model=sam3-image</a> 2026-09-12T22:05:39Z https://njump.cloud.vinney.xyz/nevent1qqs22swrew0jpwctl0cg540htsuzxx7pnekh9cnu965um43gak62regzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x96d3kq MiniMax H3 Max now supports reference-based video generation on NanoGPT.<br/><br/>Guide a new shot with image, video and audio references, alongside the existing text and first/last-frame modes.<br/><br/><a href="https://nano-gpt.com/media?mode=video&amp;model=minimax%2Fh3-max">https://nano-gpt.com/media?mode=video&amp;model=minimax%2Fh3-max</a> 2026-09-12T13:47:27Z https://njump.cloud.vinney.xyz/nevent1qqsr0gxgmzfyd5pq737cw3gqnrh2jaw2vnz6kd3mzvykqshczdkutuszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xxvtgy0 Grok Imagine Video 1.5 now supports text-to-video, image animation and reference-image generation on NanoGPT.<br/><br/>Start from a prompt or guide your scene with reference images.<br/><br/><a href="https://nano-gpt.com/media?mode=video&amp;model=xai%2Fgrok-imagine-video%2Fv1.5%2Fimage-to-video">https://nano-gpt.com/media?mode=video&amp;model=xai%2Fgrok-imagine-video%2Fv1.5%2Fimage-to-video</a> 2026-09-12T09:42:43Z https://njump.cloud.vinney.xyz/nevent1qqs2d6dgrqhc8pzupnns8rn6qtst0rv6js6fdf8m5pnj9lgkj5f5dpgzyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xl4zzec ElevenLabs Music and Sound Effects V2 are now on NanoGPT.<br/><br/>Create songs with vocals, instrumental soundtracks, sound effects and seamless loops from text prompts.<br/><br/><a href="https://nano-gpt.com/media?mode=audio&amp;audioMode=tts&amp;model=elevenlabs%2Fmusic">https://nano-gpt.com/media?mode=audio&amp;audioMode=tts&amp;model=elevenlabs%2Fmusic</a> 2026-09-12T05:44:43Z https://njump.cloud.vinney.xyz/nevent1qqstg4na5n4y8436zm6td455slgn3t9v8uetyjj4y25kxnpge9k7wmszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x7zjguq Connection dropped during image generation?<br/><br/>NanoGPT can now recover completed images from supported jobs into your chat history. Reopening a conversation also resumes checking pending generations.<br/><br/><a href="https://nano-gpt.com/updates">https://nano-gpt.com/updates</a> 2026-09-08T16:24:09Z https://njump.cloud.vinney.xyz/nevent1qqsf8g9t964wht8qu7j7rnmh32jvhptdk6nhv9m2ttpg4qkkxvfva6szyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x84d8mr Gonka24 is now on NanoGPT.<br/><br/>Access MiniMax M2.7 and DeepSeek V4 Flash 0731 through the Gonka inference network, with streaming and reasoning.<br/><br/>Select Gonka24 or use :gonkaai in API model names. These routes do not guarantee zero data retention.<br/><br/><a href="https://nano-gpt.com/provider/gonkaai">https://nano-gpt.com/provider/gonkaai</a> 2026-09-08T13:01:35Z https://njump.cloud.vinney.xyz/nevent1qqsdmwmnc2s6da376xexycc4qwmw5dheh40q8ty437c273x3ccvvxlszyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4x4f8nmf NanoGPT can now auto-delete old chats.<br/><br/>Opt in to permanently delete conversations after 30 inactive days, including synced cloud copies. Project conversations are kept. Off by default.<br/><br/>Find it in Storage and Sync settings:<br/><a href="https://nano-gpt.com/settings">https://nano-gpt.com/settings</a> 2026-09-06T05:12:39Z https://njump.cloud.vinney.xyz/nevent1qqswjc3hjce5ps9k3q9ay3ezh4hptw0pmuvdkcww6gfs4j739snerwczyp3f9hwrxnmkjf45rmhx00lrjgh60glte8wjj6ev8tszna0tw4u4xjdsacz Abliterated Model Large V2 now supports native tool calling and structured output on NanoGPT.<br/><br/>The unrestricted GLM-5.3-based model also supports prompt caching and has a 1M-token context.<br/><br/>Try it:<br/><a href="https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model-large-v2">https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model-large-v2</a> 2026-09-04T15:39:36Z