Get a quote

Validate input and estimate credits / 校验与估价

curl --request POST \
  --url https://apistable.com/v1/quotes \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "prism-image-2",
  "input": {
    "prompt": "<string>",
    "duration_seconds": 123,
    "resolution": "<string>",
    "seed": 1,
    "generate_audio": true,
    "instrumental": true,
    "lyrics": "<string>"
  },
  "output_count": 1,
  "fallback": false,
  "max_credits": 1
}
'

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'prism-image-2',
    input: {
      prompt: '<string>',
      duration_seconds: 123,
      resolution: '<string>',
      seed: 1,
      generate_audio: true,
      instrumental: true,
      lyrics: '<string>'
    },
    output_count: 1,
    fallback: false,
    max_credits: 1
  })
};

fetch('https://apistable.com/v1/quotes', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://apistable.com/v1/quotes"

payload = {
    "model": "prism-image-2",
    "input": {
        "prompt": "<string>",
        "duration_seconds": 123,
        "resolution": "<string>",
        "seed": 1,
        "generate_audio": True,
        "instrumental": True,
        "lyrics": "<string>"
    },
    "output_count": 1,
    "fallback": False,
    "max_credits": 1
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "is_preview": true,
  "model": "<string>",
  "input": {
    "prompt": "<string>",
    "duration_seconds": 123,
    "resolution": "<string>",
    "aspect_ratio": "16:9",
    "seed": 1,
    "generate_audio": true,
    "instrumental": true,
    "lyrics": "<string>"
  },
  "output_count": 2,
  "estimated_credits": 1,
  "max_reserved_credits": 1,
  "channel_quotes": [
    {
      "channel_type": "third_party",
      "credits": 1
    }
  ],
  "price_version": "<string>",
  "live_available": false
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

POST

quotes

Validate input and estimate credits / 校验与估价

curl --request POST \
  --url https://apistable.com/v1/quotes \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "prism-image-2",
  "input": {
    "prompt": "<string>",
    "duration_seconds": 123,
    "resolution": "<string>",
    "seed": 1,
    "generate_audio": true,
    "instrumental": true,
    "lyrics": "<string>"
  },
  "output_count": 1,
  "fallback": false,
  "max_credits": 1
}
'

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'prism-image-2',
    input: {
      prompt: '<string>',
      duration_seconds: 123,
      resolution: '<string>',
      seed: 1,
      generate_audio: true,
      instrumental: true,
      lyrics: '<string>'
    },
    output_count: 1,
    fallback: false,
    max_credits: 1
  })
};

fetch('https://apistable.com/v1/quotes', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://apistable.com/v1/quotes"

payload = {
    "model": "prism-image-2",
    "input": {
        "prompt": "<string>",
        "duration_seconds": 123,
        "resolution": "<string>",
        "seed": 1,
        "generate_audio": True,
        "instrumental": True,
        "lyrics": "<string>"
    },
    "output_count": 1,
    "fallback": False,
    "max_credits": 1
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "is_preview": true,
  "model": "<string>",
  "input": {
    "prompt": "<string>",
    "duration_seconds": 123,
    "resolution": "<string>",
    "aspect_ratio": "16:9",
    "seed": 1,
    "generate_audio": true,
    "instrumental": true,
    "lyrics": "<string>"
  },
  "output_count": 2,
  "estimated_credits": 1,
  "max_reserved_credits": 1,
  "channel_quotes": [
    {
      "channel_type": "third_party",
      "credits": 1
    }
  ],
  "price_version": "<string>",
  "live_available": false
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

API preview: generation providers are not connected. An authenticated request can return 503 without creating a task or charging credits.

Quote the complete input

The server normalizes defaults, filters incompatible channels, and applies each remaining channel’s pricing formula. Duration, resolution, audio, quality, and output_count may all change the total. The maximum reservation covers one successful route per result item, not the sum of every possible failed attempt. A quote is an estimate of accepted limits, not a promise that a preview model will run.

Understand the upper bound

{
  "is_preview": true,
  "model": "prism-image-2",
  "input": {
    "prompt": "A sculptural chair in warm afternoon light",
    "resolution": "1024"
  },
  "output_count": 4,
  "estimated_credits": 80,
  "max_reserved_credits": 240,
  "channel_quotes": [
    {
      "channel_type": "third_party",
      "credits": 80
    },
    {
      "channel_type": "official",
      "credits": 240
    }
  ],
  "price_version": "preview-2026-10-29",
  "live_available": false
}

channel_quotes[].credits is the total for the whole batch on that route, not a per-item price. This endpoint returns an unreserved preview estimate, not a quote_id or a locked purchase offer.

Set max_credits

max_credits is your cap for the entire request. If the server’s maximum reservation is higher, it rejects the whole submission before any generation. It does not silently reduce output_count or divide a smaller budget between items.

Body

application/json

model

string

required

Minimum string length: 1

Example:

"prism-image-2"

input

object

required

Current preview input. Supported fields vary by modality and exact catalog model. No live provider mapping is implied.

Show child attributes

output_count

integer

default:1

Target result count. Images/videos accept 1–4; music and LLM must remain 1. Not a concurrency guarantee. / 目标结果数，非同时并发保证。

Required range: 1 <= x <= 4

fallback

boolean

default:false

Authorizes a higher-priced compatible official fallback after an eligible confirmed failure. Live execution is disabled in this build.

max_credits

integer

Whole-request reservation cap. Reject the entire request when max_reserved_credits exceeds it.

Required range: x >= 0

Response

Preview quote

is_preview

any

required

model

string

required

input

object

required

Current preview input. Supported fields vary by modality and exact catalog model. No live provider mapping is implied.

Show child attributes

output_count

integer

required

Required range: 1 <= x <= 4

estimated_credits

number

required

Credits, not USD. / 积分，非美元。

Required range: x >= 0

max_reserved_credits

number

required

Credits, not USD. / 积分，非美元。

Required range: x >= 0

channel_quotes

object[]

required

Show child attributes

price_version

string

required

live_available

any

required

Get started

API reference

Core concepts

Quote the complete input

Understand the upper bound

Set max_credits

Body

Response

​Quote the complete input

​Understand the upper bound

​Set max_credits

Body

Response

Quote the complete input

Understand the upper bound

Set max_credits