Pika 2.5
Pika's current generation model, available as both text-to-video and image-to-video on the Pika API and in the Pika consumer app.
- Resolution
- 1080p
- Weights
- Not released
- API
- Yes
- Commercial use
- Permitted subject to conditions
Outputs 720p or 1080p; Pika's pricing page states maximum video duration ranges from 5 to 25 seconds depending on the feature and resolution used, with longer clips built through Pikaframes.
Free tier is watermarked and explicitly excludes commercial use.
- The free tier is non-commercial. Free tier is watermarked and explicitly excludes commercial use
- Depends on your plan tier. Commercial use is permitted on Standard and above, which also remove the watermark
- Output is watermarked. Free tier is watermarked and explicitly excludes commercial use
Specification
- What it takes in
- text, image
- What it makes
- video
- Maximum duration
- not established
- Maximum resolution
- 1080p
- Aspect ratios
- not established
- Controls
- image-to-video, extend, keyframes
- Weights
- Not released
- API
- Yes
- Pricing
- API per second of output: $0.04/sec at 720p, $0.09/sec at 1080p. Consumer app is credit-based: Free 80 monthly credits (480p, image-to-video only, watermarked, no commercial use), Standard $8/mo yearly 700 credits, Pro $28/mo 2,300 credits, Fancy $76/mo 6,000 credits; video generation costs 12-80 credits per video
- Released or updated
- not established
Maximum duration and supported aspect ratios are not established here. That means no page we could retrieve stated them, not that the model lacks them.
Strengths
- Among the cheapest per-second video APIs at $0.04/sec (720p)
- Both text-to-video and image-to-video paths
- Generous free tier for experimentation
- Sits alongside Pika's effect and edit tools in one platform
Weaknesses
- Per-generation duration limits are not published as explicit enums on Pika's own pages
- No native audio generation documented
- Free tier is 480p, watermarked and non-commercial
- Aspect ratio options are not documented on the pages fetched
- Model generation is behind the current frontier (Pika 2.5 dates from 2025)
Best for
- short-form social video
- cheap high-volume generation
- effect-led clips
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- Pika's consumer pricing page states maximum duration is "5-25 seconds depending on feature and resolution" without per-model detail, while third-party pages claim 5-10s per generation extendable to 25s with Pikaframes; Pika's API pricing page shows only a 5s reference row - https://pika.art/pricing vs https://dev.pika.art/pricing
- Pika's API pricing lists a single 5s row per resolution, so whether longer single generations are billable per second beyond 5s is unverified - https://dev.pika.art/pricing
MCP servers that front Pika
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
Filtrix AI MCP
Filtrix MCP for image/video generation. Portal.
-
Picsart GenAI
Generate and edit images, videos and audio with 150+ AI models.
-
Shortgenius
Generate AI short-form videos and auto-publish them to TikTok, YouTube, Instagram, Facebook and X.
-
Varosity
One key for AI video, voice, music, and image across 40+ frontier models. BYOK zero markup.
-
Vivideo
AI video generation via the Vivideo API: auto or manual mode, avatars, voices, brand kits.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
Pika 2.5 Keyframe
Keyframe-driven variant of Pika 2.5, exposed as an image-to-video model on the Pika API. It interpolates between supplied frames rather than generatin
Video generation
Adobe Firefly Video Model
The Adobe Firefly Video Model generates video from a text prompt, optionally guided by an image used as the first or final frame. Adobe's Firefly Serv
Video generation
Allegro
A small text-to-video model comprising a 2.8B VideoDiT and a 175M VideoVAE, released under Apache-2.0 in October 2024. It generates 88-frame clips at
Video generation