9 models · video and image
FLUX API
FLUX is a family of AI video and image models made by Black Forest Labs. varg runs 9 of them on one API key: FLUX 3, Flux 3 Image, FLUX 3 Draft and 6 more. Between them they cover text to video, image to video, video to video, text to image and image to image; they return video and images.
- Price
- From $0.01 per run Flux 3 Image Klein
- FLUX 3
- From $0.85 per run
- Made by
- Black Forest Labs
- Flagship id
flux_3
Every FLUX model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux_3",
"prompt": "A red panda walks along a mossy log in a sunlit forest, one continuous unbroken shot. Ambient birdsong and rustling leaves.",
"resolution": "720p",
"duration": 5
}'FLUX models and prices
FLUX on varg starts from $0.01 per run (Flux 3 Image Klein). Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
FLUX 3flux_ | Black Forest Labs FLUX 3. Latest flagship video model — text-to-video, image-to-video, and video-to-video with native audio. 720p/1080p, 5-10s. | Text to video, Image to video, Video to video | From $0.85 per runfrom $0.17/s | ~60 s |
Flux 3 Imageflux_ | Black Forest Labs FLUX 3 Image. Newest image model — native 2K/4K, precise layout control, improved text rendering. Edits with up to 10 references. | Text to image, Image to image | From $0.02 per run$0.048/MP | ~30 s |
FLUX 3 Draftflux_ | Black Forest Labs FLUX 3 Draft. Fast ~1/3 cost preview mode for FLUX 3 — text-to-video, image-to-video, video-to-video. HD only, 5-10s. | Text to video, Image to video, Video to video | From $0.30 per run$0.06/s | ~30 s |
FLUX 3 Maxflux_ | FLUX 3 Max by fal × Black Forest Labs. Top-tier image-to-video at near real-time speed: 5-20 seconds at 720p or 1080p with native audio, first/last… | Text to video, Image to video | From $0.85 per runfrom $0.17/s | ~60 s |
Flux 3 Image Kleinflux_ | Black Forest Labs FLUX 3 Image Klein. Compact open-weights FLUX 3 Image (5.6B): native 4K, bounding-box layout, edits with up to 10 references. | Text to image, Image to image | From $0.01 per runfrom $0.01/image | ~5 s |
Flux Devflux_ | Flux Dev. Good quality at lower cost. | Text to image | From $0.01 per run$0.04/MP | ~15 s |
Flux Proflux_ | Black Forest Labs Flux Pro 1.1. High-quality image generation. | Text to image | From $0.01 per run$0.04/MP | ~15 s |
Flux Schnellflux_ | Flux Schnell. | Text to image | From $0.01 per run$0.0027/MP | ~5 s |
Flux Schnell (PiAPI)flux_ | Flux Schnell via PiAPI provider. Alternative routing for Flux Schnell. | Text to image | From $0.01 per run$0.003/MP | ~15 s |
Call the FLUX API
The call below runs FLUX 3. For another FLUX model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux_3",
"prompt": "A red panda walks along a mossy log in a sunlit forest, one continuous unbroken shot. Ambient birdsong and rustling leaves.",
"resolution": "720p",
"duration": 5
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs FLUX 3 with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "video",
"input": {
"model": "flux_3",
"prompt": "A red panda walks along a mossy log in a sunlit forest, one continuous unbroken shot. Ambient birdsong and rustling leaves.",
"resolution": "720p",
"duration": 5
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool video '{"model":"flux_3","prompt":"A red panda walks along a mossy log in a sunlit forest, one continuous unbroken shot. Ambient birdsong and rustling leaves.","resolution":"720p","duration":5}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
FLUX compared
Price, limits and inputs side by side, from the same catalog as this page.
How to use FLUX
Step-by-step pages on varg how to.
FLUX API: questions
- How much does the FLUX API cost on varg?
- The lowest price the catalog states in the FLUX family is from $0.01 per run, on Flux 3 Image Klein, Flux Dev, Flux Pro, Flux Schnell and Flux Schnell (PiAPI). Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which FLUX models are on varg?
- 9: FLUX 3 (from $0.85 per run), Flux 3 Image (from $0.02 per run), FLUX 3 Draft (from $0.30 per run), FLUX 3 Max (from $0.85 per run), Flux 3 Image Klein (from $0.01 per run), Flux Dev (from $0.01 per run), Flux Pro (from $0.01 per run), Flux Schnell (from $0.01 per run) and Flux Schnell (PiAPI) (from $0.01 per run). Each has its own page with the parameters and a call to copy.
- Which FLUX models take an image?
- 5 of the 9: FLUX 3, Flux 3 Image, FLUX 3 Draft, FLUX 3 Max and Flux 3 Image Klein. The catalog lists image to video and image to image for them; pass the image as a URL in "files".
- What is the longest clip the FLUX models make?
- 20 seconds, on FLUX 3, FLUX 3 Draft and FLUX 3 Max, by the models' input schemas.
- Which FLUX models generate audio?
- 2 of the 9: FLUX 3 and FLUX 3 Max. Set "audio": true in the request and the video comes with a native audio track. The input schemas of the others state no audio switch; each model page says what that model returns.
- How long do FLUX requests take?
- Typically from about 5 s (Flux 3 Image Klein) to about 60 s (FLUX 3), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the FLUX API?
- Send POST https://api.varg.ai/v2/tools/video/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "flux_3". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use FLUX from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "video" and the model id, for example "model": "flux_3".
More model APIs
Same API key, same request shape: change the model string to switch.
- AI video API
- AI image API
- Kling API
- Veo API
- Seedance API
- Wan API
- GPT Image API
- Nano Banana API
- Seedream API
- MiniMax API
- HeyGen API
- Grok Imagine API
- Gemini Omni API
- OmniHuman API
- PixVerse API
- LTX API
- Kandinsky API
- Vidu API
- Happy Horse API
- Sync lipsync API
- ID-V2V API
- Topaz API
- SeedVR API
- Krea API
- Ideogram API
- Recraft API
- Bria API
- Qwen Image API
- Phota API
- Higgsfield Soul API
For AI agents: each model above has its full spec as Markdown at varg.ai/models/flux_3.md (swap the id), and every model is listed in varg.ai/models/llms.txt.