Place to run it · Pictures, Video, Voice and speech
Runpod
Rents graphics cards (GPUs) by the second so you can run AI models yourself, plus ready-made endpoints for popular image, video and speech models. Aimed at developers; no subscription.
At a glance
- Open or closed
- ClosedOnly usable through the maker's app or APIHosting service is proprietary; openness of hosted models varies.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Licence
- Runpod Terms of Service (The maker's own terms)source · checked 12 Oct 2026 · checked on the maker's own page
- Can I sell what I make?
- Depends on the model you chooseRunpod claims no ownership of your content; output rights depend on each model's licence.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Cost
- No free plan.Plans below.
- How you use it
- Maker's own API, In your browserWeb console for pods; API for serverless and public endpoints; Hub of open-source templates.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Skill needed
- TechnicalInferred: you manage GPU machines or call an API.source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
- Made by
- Runpod, Inc. (US)Address: 329 Bryant St, San Francisco, United States.source · checked 12 Oct 2026 · checked on the maker's own page
- Status
- Availablesource · checked 12 Oct 2026 · checked on the maker's own page
What you can make with it
- A picture, from a description (main use)
- A picture, by changing a photo I have
- A video, from a description
- A video, by bringing a photo to life
- A voice or speech, read my text aloud
- A voice or speech, text from a recording
text to imageimage to imagetext to videoimage to videotext to audioaudio to texttext to text
Plans and prices
| Plan | Price | Includes |
|---|---|---|
| Pod: RTX 4090 (24 GB) | $0.89 per hours of fast generation | Per hour on demand, billed by the second. Commercial use: Depends on the model you choose |
| Pod: H100 80 GB PCIe | $2.89 per hours of fast generation | Per hour on demand. Commercial use: Depends on the model you choose |
| Serverless: RTX 4090 | $1.10 per hours of fast generation | Per hour, billed by the second. Commercial use: Depends on the model you choose |
| Public endpoint: Qwen Image | $0.02 per image | Per request. Commercial use: Depends on the model you choose |
| Public endpoint: FLUX.1 [dev] | $0.02 per megapixel | Per megapixel. Commercial use: Depends on the model you choose |
| Public endpoint: Wan 2.2 T2V 720p | $0.30 per results (approximate) | Per 5-second 720p video. Commercial use: Depends on the model you choose |
Some plans are not listed here; see the source for the full list.
Rough cost of one standard image: about $0.02 / £0.015 (estimate, worked out by Plainly, not a price the maker publishes). Qwen Image public endpoint at $0.02 per request (one image). GBP at 0.75.
Rough cost of 5 seconds of 720p video: about $0.30 / £0.225 (estimate, worked out by Plainly, not a price the maker publishes). Wan 2.2 text-to-video 720p, 5 s at $0.30 per request. GBP at 0.75.
Rights and safety
- Trains on your work?
- The terms don't say clearlyTerms let Runpod use content in aggregated, anonymized form to improve the service; model training not mentioned.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Related
Models you can run here
Qwen-Image, FLUX.1 [dev], FLUX.1 Kontext, FLUX.1 [schnell], Seedream 4.0, Gemini 2.5 Flash Image (Nano Banana), Wan 2.1, Wan 2.2, Seedance, Whisper, Chatterbox
Other options for “A picture, from a description”
Adobe Express, Adobe Firefly, Adobe Photoshop, Akool, Artbreeder, Bria, Canva AI (Magic Studio), ChatGPT Images, Civitai, Clipdrop, ComfyUI, Creatify, DeeVid AI, DiffusionBee, DomoAI, Draw Things, Dreamina, Dzine, fal, Filmora, FlexClip, FLUX.1 [dev], FLUX.1 [schnell], FLUX.1 Kontext
About this entry
Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.