pika-h3-flex
model id: pika/pika-h3-flex
Playground
Only one of these two tabs is sent — a model can't take both a start/end image and reference files in the same call.
Output
Price
From $0.01 / second
per second of generated video — price depends on requested size/resolution
Resolution (via size) | Price |
|---|---|
| 480p | $0.01 / second |
| 768p | $0.02 / second |
| 1080p | $0.035 / second |
| 2k | $0.04 / second |
| 4k | $0.08 / second |
Same rate as text-to-video above — attaching a starting image never changes the price.
Reference-to-video bills its own rate below — whether you attach reference images, a reference video, or both:
| 480p | $0.03 / second |
| 768p | $0.06 / second |
| 1080p | $0.075 / second |
| 2k | $0.08 / second |
| 4k | $0.1 / second |
+ VideoRouter platform fee: 2.5% of provider cost (≈ $0.0003) — billed as its own line, never blended into the price above.
# create
import requests
resp = requests.post(
"https://videorouter.sh/api/v1/videos",
headers={"Authorization": "Bearer llmr_sk_...", "Content-Type": "application/json"},
json={"model": "pika/pika-h3-flex", "prompt": "A drone shot flying over snowy mountains", "duration_secs": 5},
)
job = resp.json()
# poll
status = requests.get(
f"https://videorouter.sh/api/v1/videos/{job['id']}",
headers={"Authorization": "Bearer llmr_sk_..."},
).json()
print(status["status"]) # pending -> in_progress -> completed
Customer reviews
Specific to the Pika hosting of pika-h3-flex — other providers serving the same model have their own reviews.
Log in to write a review of pika-h3-flex.
No reviews yet — be the first to share how this model performed for you.
Guides & comparisons
- fal.ai vs VideoRouter: What Seedance 2.5, Seedance 2.0, Wan 3.0, MiniMax H3 and Kling 4.0 Cost on Each
- How to Call the MiniMax H3 API (Python + curl, Provider Pinning Explained)
- MiniMax H3 API Pricing: Every Provider Compared
- MiniMax H3 vs Kling v3.0: Which Costs Less?
- Video generation API for developers
- Live video API price index