Examples for using wan-2.7-text-to-video through RunAPI from agent tools or API calls. Copy a prompt, then use it in Claude Code, Codex, Cursor, Windsurf, or your backend.
1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. Restart Claude Code
3. Paste this prompt: Generate a video: "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
1. codex plugin install runapi-mcp@agents
2. Restart Codex
3. Paste this prompt: Generate a video: "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
1. npx @runapi.ai/mcp init cursor
2. Restart Cursor
3. Paste this prompt: Generate a video: "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
1. npx @runapi.ai/mcp init windsurf
2. Restart Windsurf
3. Paste this prompt: Generate a video: "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
curl -X POST https://runapi.ai/api/v1/wan/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "wan-2.7-text-to-video",
"prompt": "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
}
JSON
import { WanClient } from "@runapi.ai/wan";
const client = new WanClient({
apiKey: process.env.RUNAPI_API_KEY,
});
const result = await client.textToVideo.run({
"model": "wan-2.7-text-to-video",
"prompt": "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
});
console.log(result.id);
require "runapi/wan"
client = RunApi::Wan::Client.new
result = client.text_to_video.run(
model: "wan-2.7-text-to-video",
prompt: "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
)
puts result.id
package main
import (
"context"
"fmt"
"log"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader("{\"model\":\"wan-2.7-text-to-video\",\"prompt\":\"In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating.\"}")
req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/wan/text_to_video", body)
if err != nil {
log.Fatal(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer resp.Body.Close()
fmt.Println(resp.Status)
}
wan-2.7-text-to-video/api/v1/wan/text_to_videoGet API Key
In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating.
curl -X POST https://runapi.ai/api/v1/wan/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "wan-2.7-text-to-video",
"prompt": "In the depths of a dense tropical jungle with dappled sunlight filtering through leaves, an explorer in a khaki jacket kneels brushing soil from ancient fragments, reveals shimmering symbols. Camera pushes from wide angle to close-up of his brown pupils dilating."
}
JSON
Impressionist style, dusk, soft light, side light, low saturation, cold tone, center composition, medium shot, following shot. Watercolor-style fox walks slowly through forest, figure dissolving and integrating with blurred forest colors.
Backlight, medium shot, sunset, soft light, silhouette, center composition, orbiting shot, the lens follows the character from back to front showing rugged cowboy clutching holster, looking alertly around desolate western ghost town.
curl -X POST https://runapi.ai/api/v1/wan/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "wan-2.7-text-to-video",
"prompt": "Backlight, medium shot, sunset, soft light, silhouette, center composition, orbiting shot, the lens follows the character from back to front showing rugged cowboy clutching holster, looking alertly around desolate western ghost town."
}
JSON
Drone lens, fast passing through, looking up from the inside of a circular pipe covered with frost and cracks. Then, the lens flies out of pipe revealing polar snowfield at sunrise with golden light.
curl -X POST https://runapi.ai/api/v1/wan/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "wan-2.7-text-to-video",
"prompt": "Drone lens, fast passing through, looking up from the inside of a circular pipe covered with frost and cracks. Then, the lens flies out of pipe revealing polar snowfield at sunrise with golden light."
}
JSON
Abstract motion graphics of a floating sphere of liquid mercury that continuously morphs between geometric shapes — sphere to cube to tetrahedron to torus and back to sphere. Each transition is smooth and organic, with the reflective surface rippling and stretching. The metallic surface reflects a colorful studio environment with pink and blue gradient lighting visible in the reflections. The object floats in the center of frame against a soft gradient background that shifts from deep purple at the bottom to pale lavender at the top. Slow, hypnotic movement. Perfect loop.
curl -X POST https://runapi.ai/api/v1/wan/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "wan-2.7-text-to-video",
"prompt": "Abstract motion graphics of a floating sphere of liquid mercury that continuously morphs between geometric shapes — sphere to cube to tetrahedron to torus and back to sphere. Each transition is smooth and organic, with the reflective surface rippling and stretching. The metallic surface reflects a colorful studio environment with pink and blue gradient lighting visible in the reflections. The object floats in the center of frame against a soft gradient background that shifts from deep purple at the bottom to pale lavender at the top. Slow, hypnotic movement. Perfect loop."
}
JSON
FAQ
Using wan-2.7-text-to-video prompts
What is %{model}?
%{model} is available through RunAPI as part of the unified model catalog. These prompts show practical input patterns that agents and backend services can reuse.
How do I use these prompts?
Copy any prompt and paste it into Claude Code, Codex, Cursor, or Windsurf after installing the RunAPI MCP Server. Developers can also copy the API example and send the prompt directly.
Do these prompts cost money to browse?
Browsing and copying prompt examples is free. Generation requests only cost money when you call a RunAPI model with your API key.
Can I adapt the prompts for production?
Yes. Treat each prompt as a starting point, then add your brand rules, output dimensions, safety constraints, and application-specific context before using it in production.