Nano-GPT

Don't want to connect Gmail or Outlook to AI? Now you don't have to. NanoGPT gives you your own email address: forward any email to it, then ask about it in any chat. Encrypted when it arrives. Only your passkey can open it. Set it up in Workspace → Incoming email, or in a chat choose + → Email

Shot it vertically. Need it wide? LTX-2.5 Reframe is now on NanoGPT. It generates beyond the edges of your video, keeping the whole original shot visible. Five aspect ratios, 720p or 1080p. Clips up to 60 seconds. nano-gpt.com/studio?model=li…

The poster works. The wording doesn't. MiniMax H3 Image is now on NanoGPT. Upload an image and describe the edit, or start from a prompt. Up to 2K, with 15 aspect ratios. $0.03 per generated image. $0.04 per edit. nano-gpt.com/studio/image?mo…

Gemini 4 Carbon is now available on NanoGPT! nano-gpt.com/conversation?mo…

Claude Fable 5.2 is now on NanoGPT. Anthropic reports 49.1% on FrontierCode 2.0 at Xhigh effort and 69.9% on FrontierSWE v2. It supports text, images and PDFs, tool calling, structured output, a 1M-token context and up to 128K output tokens. Anthropic retains prompts and outputs for 30 days; zero data retention is unavailable for this model on NanoGPT. nano-gpt.com/conversation?mo…

Turn a single photo into a textured 3D mesh. MoGe 3 is now on NanoGPT. It reconstructs visible scene geometry and gives you a GLB mesh, colored point cloud, depth and surface-normal maps, and camera data. nano-gpt.com/studio?model=mi…

You can now choose your fallback models on the NanoGPT API. Send an ordered "models" list through Chat Completions, Responses or Messages. A request can try up to four models when a provider fails before the response starts. Examples and supported combinations: docs.nano-gpt.com/api-refere…

Gemini Omni 1.2 Flash is now on NanoGPT. Create 3–15-second videos with native audio, guide scenes with up to six reference images, or animate between a first and last frame. You can also edit existing clips and extend videos up to 30 seconds total. nano-gpt.com/studio?model=go…

LTX-2.3 Fast and Pro are now on NanoGPT. Turn text or an image into video with synchronized audio. Guide the opening and ending frames, choose portrait or landscape, and output at up to 4K. Fast supports even durations from 6 to 20 seconds; Pro offers 6, 8 or 10 seconds. nano-gpt.com/studio?model=li…

Split one image into separate transparent layers. Seedream 5.5 is now on NanoGPT, with layer decomposition alongside image generation and editing with up to 10 reference images. Generate images at up to 3K, or break an existing image into a base image and transparent PNG layers at up to 2K. nano-gpt.com/studio?model=by…

Not sure which image model you need? You don’t have to know. nano-gpt.com/models/image now starts with what you want to do: - Describe an image - Edit with a prompt - Text & logos - Upscale - Reuse a character - Remove the background Pick the task and get the models that do it!

GPT Image 2.6 Flare and Sunburst are now on NanoGPT. Generate or edit with up to 16 reference images, sizes up to 4K, transparent backgrounds, and separate quality and complexity controls. nano-gpt.com/studio?model=gp…

ElevenLabs Sound Effects V3 is now on NanoGPT. Create sound effects from text. Choose 0.5–30 seconds or automatic duration, adjust prompt influence, and generate seamless loops. Download MP3 or Opus. nano-gpt.com/studio/audio?mo…

Tencent Hy4 is now on NanoGPT. Text and image input, a 1M-token context window, tool calling and structured output. Use it for coding and long-document analysis, with high, low or no reasoning. nano-gpt.com/conversation?mo…

Tripo H3.0 is now on NanoGPT. Create a 3D model from text, one image, or 2–4 views. Up to 2M triangle faces, optional PBR textures up to 8K, and low-poly controls. GLB or FBX, depending on topology.

Topaz image tools are now on NanoGPT. Upscale with 18 algorithms, enlarge transparent images 4x, remove noise with Denoise Max, or recover blurred detail with Super Focus.