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.
Filtering by: multimodal · clear filter
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.
Who said what, and what needs doing next?
Qwen3.8 Omni Flash is now on NanoGPT. Analyze audio, video, images and text for meeting summaries, transcripts and action items.
Nearly 1M context, reasoning and tool calling.
https://nano-gpt.com/conversation?model=qwen%2Fqwen3.8-omni-flash
Ling 3.0 Flash VL is now on NanoGPT and included in your subscription.
Analyze images, charts, documents and videos with reasoning and tool calling.
256K context, with 5.5B active parameters.
https://nano-gpt.com/conversation?model=inclusionai%2Fling-3.0-flash-vl
More open-source models now support NanoGPT Flex and Batch requests at 50% below standard synchronous pricing.
Gemini 3.8 Flash is also available in the Batch API for text and image workloads, with per-request thinking controls.
Qwen3.8 Max 0902 is now available on NanoGPT.
The new 2.4T-parameter checkpoint supports a 1M-token context, multimodal input, selectable thinking, tool calling, structured output, and stronger coding and agent workflows.
Try it:
https://nano-gpt.com/conversation?model=alibaba%2Fqwen3.8-max-0902
Abliterated Model and Abliterated Model Large are now available on NanoGPT.
Abliterated Model supports text, images, structured output, and long-context work with a 262K context window. Abliterated Model Large is text-only, based on GLM-5.2, with a one-million-token context window for harder reasoning and long documents.
Try them:
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model-large
Meta Muse Image is now available on NanoGPT.
This image model combines high-fidelity text-to-image generation with precise image editing. Use it for detailed scenes, typography, plots, and QR codes, or upload up to 10 reference images to edit and compose people, objects, clothing, styles, and environments.
Try it:
https://nano-gpt.com/media?mode=image&model=meta%2Fmuse-image%2Ftext-to-image
Qwen 3.8 Flash Next is now available on NanoGPT and included in the subscription at 1x included-input usage.
This fast multimodal reasoning model supports text, images, and video with a 1M-token context window. It is built for coding, long documents and codebases, agent workflows, visual understanding, tool use, structured output, and long-video analysis.
Try it:
https://nano-gpt.com/conversation?model=alibaba%2Fqwen3.8-flash
GLM 5.3 Flash is now available on NanoGPT and included in the subscription at 1x usage.
Previously tested anonymously as ox-alpha, this open-weight, natively multimodal 320B reasoning model activates 18B parameters per token. It is built for efficient coding, long-running agent tasks, visual understanding, tool use, and precise long-context work.
Try it:
https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash
Qwen3.8 27B TEE is now available!
This private open-weight 27B multimodal model runs inside a Trusted Execution Environment with attestation support. It handles text, images, and video across a 262K context window and is built for reasoning, coding, tool use, structured output, and long-running professional workflows.
Try it:
Gemma 4 26B A4B Uncensored is now available on NanoGPT and included in the subscription at 1x included-input usage!
This open-weight multimodal mixture-of-experts model is tuned for fewer refusals across chat, coding, tool use, image understanding, and long-context work.
Try it:
https://nano-gpt.com/conversation?model=google%2Fgemma-4-26b-a4b-uncensored
DeepSeek V4 Flash Vision Exp is now available on NanoGPT and included in the subscription at 1x usage.
It adds image understanding while retaining reasoning, coding, tool use, agent capabilities, and a 1M-token context window.
Try it: