how much does Pika H3 Flex (self-hosted) cost?

GPU time, billed per millisecond. you pay per run from your inference shell credits. no subscription is required.

how do I run Pika H3 Flex (self-hosted) via api?

call pika/pika-h3-flex-oss with the javascript or python sdk, the rest api, or `belt app run pika/pika-h3-flex-oss` from a terminal. the api reference on this page lists every input.

who makes Pika H3 Flex (self-hosted)?

Pika H3 Flex (self-hosted) is made by pika and runs on inference shell. every pika app is listed at https://inference.sh/apps/pika.

can my agent use Pika H3 Flex (self-hosted)?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

what are the alternatives to Pika H3 Flex (self-hosted)?

other video apps on inference shell include Pika H3 Flex Upscale, Pika H3 Flex Reference to Video, Pika H3 Flex, Gemini Omni 1.2 Flash. they run through the same api, so switching is a one-line change.

Pika H3 Flex (self-hosted)

Pika H3 Flex from the open weights, on our GPUs. Text-to-video and first/last-frame image-to-video with synchronized stereo audio. 5-15s, native 480p or 768p, six sampling steps.

text to video image to video first last frame native audio open weights

run in browser →run via API run with your agent

maker: pika
category: video
input → output: text → video, image → video
runs via: api, javascript and python sdk, belt cli, mcp
updated: 2026-11-08
price: GPU time, billed per millisecond

api reference

about

pika h3 flex from the open weights, on our gpus. text-to-video and first/last-frame image-to-video with synchronized stereo audio. 5-15s, native 480p or 768p, six sampling steps.

get an api key

create one in settings → api keys. the examples read it from INFERENCE_API_KEY.

bash

1export INFERENCE_API_KEY="inf_your_key"

1. calling the api

install the client

nothing to install. any http client works; the examples use curl, and jq to read responses. every response wraps its result in a data field.

run and get result

send "wait": true to hold the connection until the task finishes. without it the call returns right away with the task still running.

bash

12# "wait": true holds the connection until the task finishes.3# the response is {"data": {"id", "status", "status_text", "output", ...}}4curl -X POST https://api.inference.sh/apps/run \5  -H "Authorization: Bearer $INFERENCE_API_KEY" \6  -H "Content-Type: application/json" \7  -d '{8    "app": "pika/pika-h3-flex-oss",9    "input": {10      "prompt": "A red fox trots along a frozen riverbank at dawn, breath steaming. 0-3s: low tracking shot beside the fox. 3-5s: it stops and looks straight into the lens. Sound: crunching snow, distant crows, no music."11    },12    "wait": true13  }'

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks. send "stream": true and the response is a server-sent event stream that ends when the task does.

bash

12# "stream": true answers with server-sent events until the task finishes3curl -N -X POST https://api.inference.sh/apps/run \4  -H "Authorization: Bearer $INFERENCE_API_KEY" \5  -H "Content-Type: application/json" \6  -d '{7    "app": "pika/pika-h3-flex-oss",8    "input": {9      "prompt": "A red fox trots along a frozen riverbank at dawn, breath steaming. 0-3s: low tracking shot beside the fox. 3-5s: it stops and looks straight into the lens. Sound: crunching snow, distant crows, no music."10    },11    "stream": true12  }'

run in the background

start the task and get its id back right away, then check on it later. for long tasks, or when you'd rather be called back, see webhooks.

bash

1# without "wait" the call returns the task right away (status 1, "received")2TASK_ID=$(curl -s -X POST https://api.inference.sh/apps/run \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "pika/pika-h3-flex-oss",7    "input": {8      "prompt": "A red fox trots along a frozen riverbank at dawn, breath steaming. 0-3s: low tracking shot beside the fox. 3-5s: it stops and looks straight into the lens. Sound: crunching snow, distant crows, no music."9    }10  }' | jq -r '.data.id')1112# later: read its state. done when status is 10 (completed), 11 (failed) or 12 (cancelled)13curl -s https://api.inference.sh/tasks/$TASK_ID \14  -H "Authorization: Bearer $INFERENCE_API_KEY" | jq '.data | {status, status_text, output}'

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

pass urls directly or use data uris for inline content.

bash

1# pass URLs or data URIs as input values2curl -X POST https://api.inference.sh/apps/run \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "pika/pika-h3-flex-oss",7    "input": {8      "image": "https://example.com/image.png",9      "audio": "data:audio/mp3;base64,..."10    },11    "wait": true12  }'

manual upload

you can also upload files manually and use the returned url.

bash

1# 1. create the file: the response has an upload_url and the file's uri2FILE=$(curl -s -X POST https://api.inference.sh/files \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{"files": [{"filename": "image.png", "content_type": "image/png"}]}')67# 2. PUT the bytes to upload_url8curl -X PUT "$(echo "$FILE" | jq -r '.data[0].upload_url')" \9  -H "Content-Type: image/png" \10  --data-binary @image.png1112# 3. pass the uri as an input value13echo "$FILE" | jq -r '.data[0].uri'

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

bash

1curl -X POST https://api.inference.sh/apps/run \2  -H "Authorization: Bearer $INFERENCE_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "app": "pika/pika-h3-flex-oss",6    "input": {7        "prompt": "A red fox trots along a frozen riverbank at dawn, breath steaming. 0-3s: low tracking shot beside the fox. 3-5s: it stops and looks straight into the lens. Sound: crunching snow, distant crows, no music."8    },9    "webhook": "https://your-server.com/webhook"10  }'

webhook payload

your endpoint receives a JSON POST with the task result:

json

1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}

eventstringtask.completed, task.failed or task.cancelled

timestampstringiso timestamp of the delivery

data.idstringtask id

data.short_idstringshort task id

data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)

data.status_textstringthe status as a word: completed, failed or cancelled

data.outputobjecttask output (when completed)

data.errorstringerror message (when failed, omitted otherwise)

data.session_idstringsession id (when the task ran in a session, omitted otherwise)

data.created_atstringiso timestamp

data.updated_atstringiso timestamp

5. schema

input

promptstring*

what happens in the video, in plain prose. describe the shots in order with timing, the camera, the subjects and the sound (dialogue in quotes, ambience, music or 'no music'). there is no prompt rewriter here, so be concrete.

example: "A red fox trots along a frozen riverbank at dawn, breath steaming. 0-3s: low tracking shot beside the fox. 3-5s: it stops and looks straight into the lens. Sound: crunching snow, distant crows, no music."minLength:1maxLength:8000

imagestring(file)

first frame (jpeg, png or webp). center-cropped to the canvas aspect ratio and held as frame one.

last_frame_imagestring(file)

last frame. can be given alone to generate up to it, or with image for first-and-last-frame.

durationinteger

requested length in whole seconds, 5 to 15. snapped up to the model's frame grid (5s gives 124 frames, 5.17s).

default: 5min:5max:15

aspect_ratiostring

canvas aspect ratio. auto follows the first keyframe when one is given, otherwise 16:9.

default: "auto"

options:"auto""21:9""16:9""3:2""4:3""5:4""1:1""4:5""3:4""2:3""9:16""9:21"

resolutionstring

native generation tier. 480p is about twice as fast.

default: "768p"

options:"480p""768p"

soundscapestring

overall ambience and physical sounds (the model's overall_soundscape field). defaults to natural sound matching the scene.

musicstring

background score (the model's non_diegetic_music field). default none.

format_promptboolean

wrap the prompt in pika's structured template (keyframe alignment line, integrated_multimodal_description, overall_soundscape, non_diegetic_music). off, or a prompt that already contains integrated_multimodal_description, is sent verbatim.

default: true

seedinteger

seed, or -1 for a random one.

default: -1min:-1

output

framesinteger*

frames generated.

heightinteger*

canvas height in pixels.

seedinteger*

seed used.

videostring(file)*

mp4 with h.264 video at 24 fps and aac stereo audio at 32 khz.

widthinteger*

canvas width in pixels.

setup

setup parameters are provided once via the setup field and are persisted for a session.

resident_transformerboolean

keep the 62 gb transformer on the gpu instead of streaming its blocks from host memory. faster, but 768p clips over 5 seconds run out of memory on an 80 gb card.

default: false

more from pika

Pika H3 Flex Audio Stems

pika/pika-h3-flex-audio-stems

$0.001/stem-sec (3 stems: dialogue, music, effect)

Pika H3 Flex Upscale

pika/pika-h3-flex-upscale

$0.05-$0.14/sec (480p src), $0.03-$0.12/sec (768p src); 1080p/2K/4K targets

Pika H3 Flex Reference to Video

pika/pika-h3-flex-reference

$0.06/sec 480p, $0.12/sec 768p, $0.15/sec 1080p, $0.16/sec 2k, $0.20/sec 4k (output+input video sec). Stems: $0.001/sec

Pika H3 Flex

pika/pika-h3-flex

$0.02/sec 480p, $0.04/sec 768p, $0.07/sec 1080p, $0.08/sec 2K, $0.16/sec 4K; stems +$0.001/stem-sec

new models

ready to run Pika H3 Flex (self-hosted)?

try in browser browse all apps

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.

products

capabilities

get started

learn

build

community

from the blog

Pika H3 Flex (self-hosted)

api reference

about

get an api key

1. calling the api

install the client

run and get result

stream live updates

run in the background

2. authentication

3. files

automatic upload

manual upload

4. webhooks

5. schema

input

output

setup

other video apps

more from pika

new models

ready to run Pika H3 Flex (self-hosted)?