Video Generation | OpenDunes Docs

The video generation endpoint produces short clips from a text prompt. Generation is asynchronous — you submit a job and poll for the result. The OpenAI Go client has no video resource, so call the endpoint directly with net/http.

Submit a generation job#

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
	"os"
)

func main() {
	body, _ := json.Marshal(map[string]any{
		"model":   "example-provider/video-model",
		"prompt":  "A lone camel walking across a vast sand dune at golden hour, cinematic wide shot.",
		"seconds": 6,
	})

	req, _ := http.NewRequest("POST", "https://opendunes.com/api/v1/videos", bytes.NewReader(body))
	req.Header.Set("Authorization", "Bearer "+os.Getenv("OPENDUNES_API_KEY"))
	req.Header.Set("Content-Type", "application/json")

	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()

	// Responds 202 with an id + poll_url
	var result map[string]any
	json.NewDecoder(resp.Body).Decode(&result)
	fmt.Println(result["id"]) // poll this
}

Poll for completion#

req, _ := http.NewRequest("GET",
	"https://opendunes.com/api/v1/videos/"+jobID,
	nil)
req.Header.Set("Authorization", "Bearer "+os.Getenv("OPENDUNES_API_KEY"))

The response includes status (queued, processing, completed, failed) and, when completed, a video.url pointing to the generated clip (signed, time-limited).

Request fields#

Field	Description
`model`	Video model slug (`?modality=video`)
`prompt`	Text description of the desired video
`seconds`	Requested clip length, 1–60 (model-dependent max)

Cost#

Billed per second of output in DA. The requested seconds is held on submission and settled on completion; a failed or timed-out job releases the full hold. See the video API reference.