Compare providers before choosing one.
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.
Clef Omni now accepts audio in NanoGPT's Decisions API.
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.
Liquid AI's LFM2.5 24B A2B is now on NanoGPT.
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.
https://nano-gpt.com/conversation?model=liquid%2Flfm-2.5-24b-a2b
Gemini 4 Argon now also has Flex and Priority tiers on NanoGPT.
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.
https://nano-gpt.com/conversation?model=google%2Fgemini-4-argon
Gemini 4 Argon is now on NanoGPT.
Google'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.
https://nano-gpt.com/conversation?model=google%2Fgemini-4-argon
A new option for creative writing and roleplay: TheDrummer's Skyfall 31B v4.2.
Now on NanoGPT with a 16K context window, included in the subscription at the standard 1x rate.
https://nano-gpt.com/conversation?model=TheDrummer%2FSkyfall-31B-v4.2
Kandinsky 6 Lite and Pro are now on NanoGPT.
Create 5-second videos with synchronized sound from a prompt or starting image. Both support English and Russian prompts. Current output is 480p.
Lite: https://nano-gpt.com/media?mode=video&model=kandinsky6-lite Pro: https://nano-gpt.com/media?mode=video&model=kandinsky6-pro
10/13/2026, 1 engagement
Route a request, pick a category or score text without generating a chat reply.
Jared Palmer's Kev 4B is now on NanoGPT's Decisions API, returning typed answers and probabilities in one forward pass.
Tell the cutout what to keep.
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.
https://nano-gpt.com/media?mode=image&model=bria%2Fremove-background-guided
Meta's Muse Wonder is live on NanoGPT.
Work with text, images, audio, video and PDFs in a 1M-token context. Reasoning, tool calling and structured output are supported.
Native computer use is now supported in NanoGPT's Responses API with GPT-6 Astra and GPT-6.1 Sol.
Your app executes the model's computer actions and sends screenshots back.
Currently supported through the native OpenAI route.
10/12/2026, 1 engagement
New in NanoGPT: "Ask me questions."
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 "Up to you."
10/12/2026, 1 engagement
GPT-6.1 Sol now supports Ultrafast on NanoGPT.
Select it in chat settings or use service_tier: "ultrafast" in API requests for faster token generation.
Ultrafast costs 6x Standard pricing.
https://nano-gpt.com/conversation?model=openai%2Fgpt-6.1-sol
NanoGPT's Decisions API now accepts images.
Classify visual content, score it, or ask yes/no questions with structured answers and probabilities.
Available with PPLX Decider v1.1, Clef and Clef Flash. Up to four images, each up to 512x512.
Run Claude jobs at 50% lower token rates with Anthropic Message Batches on NanoGPT.
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're ready.
https://docs.nano-gpt.com/api-reference/endpoint/batches#anthropic-message-batches
ACE-Step 1.5 XL Turbo is now on NanoGPT.
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.
https://nano-gpt.com/media?mode=audio&audioMode=tts&model=ACE-Step-v1.5-XL-Turbo
Qwen Image 2.1 Turbo is now on NanoGPT.
Generate and edit images with Chinese and English text, combine up to three reference images, and choose 1K or 2K output.
$0.0272 per image at either resolution.
https://nano-gpt.com/media?mode=image&model=qwen-image-2.1-turbo
ElevenLabs Audio Isolation is now on NanoGPT.
Remove background noise from speech to clean up interviews, podcasts and voice recordings.
https://nano-gpt.com/media?mode=audio&audioMode=tts&model=elevenlabs%2Faudio-isolation
Gemma 4 Chimera X Heretic and Scarlet are now on NanoGPT.
Two new finetunes for creative writing, dialogue and roleplay, with image understanding and 262K context.
Both are included in the subscription.
https://nano-gpt.com/conversation?model=gemma-4-26b-a4b-it-chimeraxheretic
https://nano-gpt.com/conversation?model=gemma-4-31b-it-scarlet
Auto Model now decides how much thinking each message needs.
Quick questions can skip reasoning; harder tasks get more. Prefer to set it yourself? Choose a fixed level with the slider, then switch Back to Auto anytime.
Make a song, then turn it into a lyrics video.
New Mureka tools on NanoGPT cover songs, instrumentals and lyric writing, plus multi-voice podcasts from a script. Lyrics videos work with generated or uploaded audio.
https://nano-gpt.com/media?mode=audio&model=mureka%2Fapi%2Fgenerate%2Fsong
Product shots, posters with readable text, or a new look for an existing image.
Nano Banana 2.1 is now on NanoGPT, with up to 14 reference images, 1K/2K output and optional Google Search grounding.
Mistral Large 4 Preview is now on NanoGPT.
Work with long documents, code and images in a 512K-token context. Supports reasoning, tool calls and structured output.
https://nano-gpt.com/conversation?model=mistralai%2Fmistral-large-4
Relight an existing video with MiniMax H3 Max Relight on NanoGPT.
Upload your clip and a lighting-sphere reference to change the look of the shot. Output options run from 480p to 2K.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Frelight
Vidu Q4 is now on NanoGPT.
Create 3-16 second videos at up to 4K. Animate an image with sound, or use up to 12 reference images and 3 voice clips to guide characters, products and voices.
Claude Haiku 5.5 now live on NanoGPT!
https://nano-gpt.com/conversation?model=anthropic%2Fclaude-haiku-5.5
Apex Flash 1 and Apex Flash 1 Abliterated are now on NanoGPT.
GLM 5.3 Flash cybersecurity finetunes for code investigation and tool use. Both included in the subscription.
Abliterated is experimental, with modified refusal behavior.
https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash-apex
Eight new Qwen 3.8 27B finetunes are now on NanoGPT: Antislop, DarkIdol, Fimi, Kimiko, Kiwen, Novelist, Swift and Synthia.
All have 262K context and are included in the subscription at the standard 1x usage rate.
Qwen Image 2.1 Pro is now on NanoGPT.
Generate images with Chinese and English text, or edit and combine up to 10 references. Native 2K output for $0.075 per image.
https://nano-gpt.com/media?mode=image&model=qwen-image-2.1-pro
Zero data retention agreements are "trust, don't verify."
That's why we built Private Mode: your prompt is encrypted on your device to an attested enclave. We can't read it, and you can check that yourself.
Editing images in NanoGPT chat has gotten much better and much simpler.
Decider 0.8B, 2B and 4B are now available through NanoGPT's Decisions API.
Classify, score and route application data with typed answers and probabilities. These models return decisions rather than generated text.
Turn a product photo into a looping video with Pixelcut on NanoGPT.
Choose subtle movement or a 360-degree spin, with a locked camera and the same image at the start and end. Create 5-15 second loops.
https://nano-gpt.com/media?mode=video&model=pixelcut%2Flooping-video
NanoGPT's Chat Completions API now accepts web_search and OpenAI's web_search_options.
Set search_context_size and user_location without rewriting your integration. Also works with OpenAI BYOK.
Marigold V2 Depth is now on NanoGPT.
Turn a single photo into a colorized depth map, without writing a prompt. See the foreground and background structure of a scene.
Workspace projects can now sync across devices on NanoGPT.
Opt in to sync projects, files, notes and tasks using your chosen storage and encryption settings. Chats sync separately; private PDFs stay local.
Building an app with Sign in with NanoGPT?
Add invitation_code to your sign-in link to refer eligible new accounts.
Waiting for a bank payment to clear?
NanoGPT now shows processing bank payments on your Balance page, including the amount and start time. Your balance is credited automatically when the payment clears. No need to submit it again.
Cloudflare's Clef is now on NanoGPT's Decisions API.
Get typed choices, scores and yes/no answers instead of generated text. Use cloudflare/clef with 16K context, billed at $0.20 per million input tokens.
SVG uploads now work in NanoGPT chats: preview the image and have the model edit the source.
Incognito chats also accept text files, including SVGs, kept in memory instead of Library or browser storage.
Share only the parts of a NanoGPT chat you choose.
New share links use snapshots encrypted on your device. Set an expiry and choose whether to include reasoning. NanoGPT cannot read the snapshot; anyone with the full link can.
Native web search is now available on supported OpenAI, Claude, Gemini and Grok models in NanoGPT.
Choose Native in the Web menu. Models without native search support fall back to Linkup.
MiniMax H3 Max Recast is now on NanoGPT.
Replace people in a video using 1-4 reference photos while preserving the original motion, camera, cuts and soundtrack. Supports 5-30 second source clips.
Individual shots must be no longer than 15 seconds.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Frecast
FLUX.3 Image is now on NanoGPT.
Generate photographs, illustrations and designs with accurate typography, with output up to 4K. Edit or combine up to 10 reference images.
Microsoft's MAI-Voice-2.1 and MAI-Voice-2.1-Flash are now on NanoGPT, with 97 voices across 23 languages.
Choose expressive long-form narration or faster speech for interactive applications.
https://nano-gpt.com/media?mode=audio&audioMode=tts&model=microsoft%2Fmai-voice-2.1
Liquid D1 is now available through NanoGPT's Decisions API.
Classify, score and route application data with typed answers and calibrated probabilities, rather than generated text. Use model liquid/d1 with POST /api/v1/decisions.
HeyGen Video 1 is now on NanoGPT.
Generate short scenes with dialogue, ambience and sound effects. Start from a prompt or image, or guide the scene with image, video and audio references.
https://nano-gpt.com/media?mode=video&model=heygen%2Fheygen-video-1
Ideogram V4.5 and V4.5 Edit are now on NanoGPT.
Create posters, logos and packaging with accurate typography, or edit existing images with reference artwork and precise control over what changes.
https://nano-gpt.com/media?mode=image&model=ideogram%2Fv4.5
https://nano-gpt.com/media?mode=image&model=ideogram%2Fv4.5%2Fedit
VEED Clean Audio is now on NanoGPT.
Remove background noise from speech recordings, adjust cleanup strength and normalize loudness. Supports recordings up to 30 minutes, with WAV or FLAC output.
https://nano-gpt.com/media?mode=audio&audioMode=tts&model=veed%2Fclean-audio
Ling 3.1 Flash is now on NanoGPT, included in the subscription.
inclusionAI's hybrid reasoning model supports coding, planning and tool use, with 256K context and up to 32K output tokens.
Thinking can be switched on or off.
https://nano-gpt.com/conversation?model=inclusionai%2Fling-3.1-flash
GPT-6.1 Sol Pro is now on NanoGPT.
The same Sol model with Pro reasoning for difficult coding, analysis and planning. 1.05M-token context, image understanding and tool calling.
https://nano-gpt.com/conversation?model=openai%2Fgpt-6.1-sol-pro
ElevenLabs v4 and v4 Turbo are now on NanoGPT.
Create expressive narration and dialogue, guide delivery with audio tags, and use custom voice IDs. Choose Turbo for lower-latency speech.
https://nano-gpt.com/media?mode=audio&audioMode=tts&model=elevenlabs%2Feleven-v4
Starting October 1, new NanoGPT text chats will open in the new interface at /chat.
Try it now:
GPT-6.1 Sol is now available on NanoGPT.
Built for complex coding, computer use and professional work, with a 1.05M-token context, image understanding, reasoning and tool calling.
https://nano-gpt.com/conversation?model=openai%2Fgpt-6.1-sol
Claude Sonnet 5.5 and Thinking are on NanoGPT.
1M context, image understanding and tool use. Anthropic reports 70.6% on Terminal-Bench 4.0 (Sonnet 5: 10.3%) and 30%+ faster output than Sonnet 5.
https://nano-gpt.com/conversation?model=anthropic%2Fclaude-sonnet-5.5
https://nano-gpt.com/conversation?model=anthropic%2Fclaude-sonnet-5.5%3Athinking
Make images and scanned PDFs searchable in NanoGPT Projects.
Choose optional paid image descriptions or OCR, see the estimate before processing, and reuse the results across Project chats.
NanoGPT API keys now support daily, weekly and monthly limits for requests, input tokens and spending, plus subscription-token allowances.
See current usage for every limit in your key settings.
CyberHeabsy is now on NanoGPT.
A lower-refusal text model for authorized security research, red-team practice, roleplay and creative writing. Optional reasoning, tool calling and a 1M-token context.
https://nano-gpt.com/conversation?model=heabsy%2Fcyberheabsy
LongCat 2.5 Preview is now on NanoGPT and included in the subscription.
Meituan's new model supports image understanding, coding, tool use and extended thinking, with a 1M-token context.
VOSR2 Image Upscaler is now on NanoGPT.
Restore and upscale photos to 2K or 4K in one pass, designed to preserve the original composition, colors, faces and fine detail.
https://nano-gpt.com/media?mode=image&model=wavespeed-ai%2Fvosr2%2Fimage
GLM 5.3 Uncensored is now on NanoGPT.
The full GLM 5.3 model, adapted for lower-refusal writing, coding, reasoning and tool use. 1M context.
Experimental: expect unusual behavior or inconsistent response quality.
https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-uncensored
Perceptron Mk1.5 is now on NanoGPT.
Understand images, video and audio, track objects across frames, and use tools to act on what the model sees. Built for visual reasoning and physical agents.
https://nano-gpt.com/conversation?model=perceptron%2Fperceptron-mk1.5
Qwen3.8 27B Uncensored TEE is now on NanoGPT.
A lower-refusal finetune for writing, coding and image analysis, with reasoning, tools and 262K context. Inference runs inside a provider-side Trusted Execution Environment.
https://nano-gpt.com/conversation?model=TEE%2Fqwen3.8-27b-uncensored
Your video doesn't have to end there.
MiniMax H3 Max Extend is now on NanoGPT. Upload a clip, describe what happens next, and request 5-15 seconds of new footage at up to 2K.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Fextend-video
Gemini 3.8 Flash TTS is now on NanoGPT.
Turn a script into expressive narration or a two-speaker conversation. Choose from 30 voices and direct the tone, pace and delivery.
https://nano-gpt.com/media?mode=audio&model=google%2Fgemini-3.8-flash-tts
Zano deposits on NanoGPT are temporarily paused.
MiMo V2.6 Flash Uncensored is now on NanoGPT.
A lower-refusal, text-only finetune with 1M context, reasoning and tool calling.
https://nano-gpt.com/conversation?model=xiaomi%2Fmimo-v2.6-flash-uncensored
Solar Mini 4 + Thinking are now on NanoGPT.
524K context; $0.05 input / $0.20 output per million tokens. PAYG only.
https://nano-gpt.com/conversation?model=upstage%2Fsolar-mini4
https://nano-gpt.com/conversation?model=upstage%2Fsolar-mini4%3Athinking
Meshy 7.1 is now on NanoGPT.
Turn a prompt, one photo or multiple views into a textured 3D asset. Text-to-3D also offers a geometry preview before creating the finished model.
https://nano-gpt.com/media?mode=3d&model=meshy%2Fv7.1%2Fimage-to-3d
9/24/2026, 1 engagement
Ember 1 is on NanoGPT in research preview.
Fireworks' Kimi K3-based model: images, tools and 1M context.
Fireworks describes Ember as a research preview, initially offered for two weeks on its serverless platform. Continued availability depends on demand.
Lumen Stealth is revealed: meet Kitani's Clover 1 150B Preview on NanoGPT.
200K context, images, reasoning and tools. Included at regular 1x subscription input usage; the 0.1x promotion has ended.
Clover remains a preview while reliability improves, so occasional interruptions are still possible. Existing Lumen Stealth chats and API IDs still work.
https://nano-gpt.com/conversation?model=kitani%2Fclover-1-150b
Aion 3.5 and Aion 3.5 Mini are now on NanoGPT for roleplay and long-form storytelling, both with 262K context.
Aion 3.5:
https://nano-gpt.com/conversation?model=aion-labs%2Faion-3.5
Aion 3.5 Mini:
https://nano-gpt.com/conversation?model=aion-labs%2Faion-3.5-mini
GPT-6 Sol and Luna now support Flex and Priority on NanoGPT, including Pro variants.
Flex: lower cost when latency matters less. Priority: higher-priority processing.
API: set service_tier to "flex" or "priority".
GPT-6 Sol:
https://nano-gpt.com/conversation?model=openai%2Fgpt-6-sol
GPT-6 Sol Pro:
https://nano-gpt.com/conversation?model=openai%2Fgpt-6-sol-pro
GPT-6 Luna:
https://nano-gpt.com/conversation?model=openai%2Fgpt-6-luna
GPT-6 Luna Pro:
https://nano-gpt.com/conversation?model=openai%2Fgpt-6-luna-pro
Qwen3.8 Max Prime is now on NanoGPT.
A higher-throughput Max variant for coding and long-running agents, with 1M context, image/video input, reasoning and tools.
$4 input / $12 output per million tokens. PAYG only.
https://nano-gpt.com/conversation?model=qwen%2Fqwen3.8-max-prime
Seedream 5.0 Flash is now on NanoGPT for fast image generation and prompt-guided edits.
Upload an image to edit it, or use Layerize to separate it into a base image and individual layers.
Generate and edit:
https://nano-gpt.com/media?mode=image&model=bytedance%2Fseedream-v5.0-flash
Layerize:
https://nano-gpt.com/media?mode=image&model=bytedance%2Fseedream%2Fv5%2Fflash%2Flayerize
Recraft V4.1 Flash is now on NanoGPT.
Fast, design-focused image generation for trying different prompts and compositions. $0.007 per image at the preset sizes.
Available in chat and the image workbench.
https://nano-gpt.com/media?mode=image&model=fal-ai%2Frecraft%2Fv4.1%2Fflash%2Ftext-to-image
Lumen Stealth is on NanoGPT for a temporary evaluation.
200K context, vision and reasoning. Included in the subscription at 0.1x input usage.
Prompts and responses are logged and may be reviewed. Do not send sensitive or confidential information.
https://nano-gpt.com/conversation?model=nano%2Flumen-stealth
GPT-6 Sol and GPT-6 Luna are now on NanoGPT.
Sol for demanding coding, reasoning and agentic work; Luna for fast chat, classification and lightweight agent workflows.
Both support image input, tool calling and a 1.05M-token context. Pay-as-you-go, not included in the subscription.
Claude Opus 5.5 is now available on NanoGPT.
Anthropic's flagship model for agentic coding, computer use and long-running tasks, with a 1M-token context, image understanding, reasoning and tool calling.
Pay-as-you-go: $4 input / $20 output per million tokens. Not included in the subscription.
https://nano-gpt.com/conversation?model=anthropic%2Fclaude-opus-5.5
Turn a reference image into a 3D asset you can keep editing.
Tripo P2 is now on NanoGPT: text-to-3D, image-to-3D, optional PBR textures and downloadable meshes for games, product mockups and Blender.
Nex N2.5 Mini + Pro are now on NanoGPT, both included in the subscription.
Open-weight coding models with vision and 262K context.
Pay-as-you-go per 1M tokens: Mini: $0.025 in / $0.10 out Pro: $0.075 in / $0.25 out
https://nano-gpt.com/conversation?model=nex-agi%2Fnex-n2.5-mini
https://nano-gpt.com/conversation?model=nex-agi%2Fnex-n2.5-pro
Lower prices for Abliterated models on NanoGPT.
Input per 1M tokens: Abliterated Model: $3 -> $1 Abliterated Model Large + Large V2: $5 -> $3
Cached input is cheaper too. Output prices are unchanged.
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model-large
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model-large-v2
Qwen Image 2.1 is now on NanoGPT: generate and edit up to 2K, combine up to 10 references, and use custom LoRAs.
From $0.02 for 1K generation and $0.03 for 1K editing with the base models. Higher resolutions and LoRA variants cost more.
https://nano-gpt.com/media?mode=image&model=qwen-image-2.1%2Fedit
Grok 4.7 is now on NanoGPT.
500K context, vision and tool calling for coding and long-running tasks.
From $1.60 input / $4.80 output per 1M tokens. Higher rates above 200K input.
Xiaomi MiMo V2.6 Flash and Pro are now available on NanoGPT and included in the subscription at 1x usage.
Both support text, images, video and audio, with a 1M-token context window, reasoning and tool calling for coding and agent workflows.
https://nano-gpt.com/conversation?model=xiaomi%2Fmimo-v2.6-flash
https://nano-gpt.com/conversation?model=xiaomi%2Fmimo-v2.6-pro
Web search is now optional in NanoGPT Private Mode, including the local proxy.
NanoGPT cannot read queries or results. Exa receives queries; Cloudflare processes fetched URLs and page contents outside the inference enclave. Search is not end-to-end confidential from those services.
Off by default. Additional search fees apply, plus model token charges.
Details:
Writing a novel, building characters, or running a long-form roleplay?
Qwen 3.8 27B Hemingway is now on NanoGPT: 262K context, image understanding and configurable reasoning.
Included in the subscription at 1x usage.
https://nano-gpt.com/conversation?model=qwen%2Fqwen3.8-27b-hemmingway
Step 5 Preview is now on NanoGPT.
StepFun's new flagship brings a 1M-token context window, image and video understanding, tool calling and structured output for coding and agent workflows.
$1 input / $2.70 output per million tokens.
https://nano-gpt.com/conversation?model=stepfun%2Fstep-5-preview
Three new options for defensive security research:
Qwen 3.8 27B, Gemma 4 26B A4B and GLM 5.3 Flash Cybersecurity are now on NanoGPT.
Image understanding + tool calling. All included in the subscription at 1x usage.
These variants retain moderation for illegal activities.
https://nano-gpt.com/conversation?model=qwen%2Fqwen3.8-27b-cybersecurity
https://nano-gpt.com/conversation?model=google%2Fgemma-4-26b-a4b-it-cybersecurity
https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash-cybersecurity
Pareto runs several AI models on your request and returns one selected or synthesized answer.
Now on NanoGPT: text + images, tool calling and 262K context.
Experimental. Its underlying model mix, behavior and performance may change.
Moderate the answer as well as the prompt.
NVIDIA Nemotron 3.5 Content Safety is now on NanoGPT: safe/unsafe classification for user messages and assistant responses, with optional reasoning.
https://nano-gpt.com/conversation?model=nvidia%2Fnemotron-3.5-content-safety
Ollama Cloud is now a provider option on NanoGPT.
Run supported models including Kimi K3, DeepSeek V4.1 Flash, GLM 5.3 Flash and Gemma 4 through Ollama.
Choose Ollama in the provider selector, or set X-Provider: ollama in API requests.
Google Lyria 3.5 is now on NanoGPT.
Describe the sound, vocals and song structure, or use an image to set the mood.
$0.11 per generation.
Try it:
https://nano-gpt.com/media?mode=audio&model=google%2Flyria-3.5
MiniMax H3 Max Lip Sync is now on NanoGPT.
Add a portrait and a voice or music track to make it talk or sing, with synchronized mouth movement and output from 480p through 2K.
Audio must be at least 5 seconds. Longer tracks are clipped to the first 15 seconds.
Try it:
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Flip-sync%2Fimage-to-video
Route the ticket. Score the answer. Choose the next action.
Jev 1.13 is now on NanoGPT's Decisions API. Send state + typed questions; get choices, scores and probabilities back.
Use /v1/decisions directly, or use a questions response format through Chat Completions, Anthropic Messages, or Responses.
API specification:
Give the video model a character, a scene and a sound to work from.
MiniMax H3 Reference-to-Video + Singularity are now on NanoGPT: guide clips with image/video/audio references, or animate a starting image.
3-15 seconds, with native stereo audio.
Reference-to-Video:
https://nano-gpt.com/media?mode=video&model=minimax-h3%2Freference-to-video
Singularity:
https://nano-gpt.com/media?mode=video&model=minimax-h3-singularity%2Fimage-to-video
Your product, in someone's hands. Your outfit, on a model.
Bria Product Holding + Virtual Try-On are now on NanoGPT.
Upload a person photo and 1-3 product or clothing references to create product shots and outfit previews from an existing scene.
Product Holding:
https://nano-gpt.com/media?mode=image&model=bria%2Fproduct-holding
Virtual Try-On:
https://nano-gpt.com/media?mode=image&model=bria%2Fvirtual-try-on
Wan 3.0 + Prime can now edit and extend videos on NanoGPT.
Restyle existing footage with a prompt, or continue a clip into a new scene.
Video Edit:
https://nano-gpt.com/media?mode=video&model=alibaba%2Fwan-3.0-prime%2Fvideo-edit
Video Extend:
https://nano-gpt.com/media?mode=video&model=alibaba%2Fwan-3.0-prime%2Fvideo-extend
27B reasoning with ternary weights.
Ternary Bonsai 2 27B is now on NanoGPT, included in the subscription.
PrismML reports 98.2% of Qwen3.8-27B's aggregate benchmark performance. With vision, tool calling and a 262K context window.
https://nano-gpt.com/conversation?model=prism-ml%2Fternary-bonsai-2-27b
Give a still image motion, sound and an ending.
Wan 3.0 Spicy + Prime Spicy are now on NanoGPT.
Create 2-30 second clips with synchronized audio and optional final-frame guidance. Prime is the faster option.
Wan 3.0 Spicy:
https://nano-gpt.com/media?mode=video&model=alibaba%2Fwan-3.0%2Fimage-to-video-spicy
Wan 3.0 Prime Spicy:
https://nano-gpt.com/media?mode=video&model=alibaba%2Fwan-3.0-prime%2Fimage-to-video-spicy