Models

The model catalog is public: GET /v1/models and GET /v1/models/{id} work without an API key. Use them to list model ids, read current prices and fetch the input schema for /v1/generate. The same data powers the models page.

List models

http

GET https://jantaris.com/v1/models

Query parameter	Values	Description
`category`	`image`, `video`, `audio`, `chat`, `tool`	Filter by category
`currency`	`USD`, `PLN`	Currency of prices in the response

bash

curl "https://jantaris.com/v1/models?category=video&currency=USD"

python

import requests

models = requests.get(
    "https://jantaris.com/v1/models",
    params={"category": "video", "currency": "USD"},
    timeout=30,
).json()["data"]

for m in models:
    print(m["id"], m["pricing"]["display"])

javascript

const res = await fetch("https://jantaris.com/v1/models?category=video&currency=USD");
const { data } = await res.json();
for (const m of data) console.log(m.id, m.pricing.display);

Response (shortened, amounts from the price list of October 2, 2026, the API returns current ones):

json

{
  "object": "list",
  "data": [
    {
      "id": "seedance-2.5",
      "object": "model",
      "name": "Seedance 2.5",
      "vendor": "ByteDance",
      "category": "video",
      "modes": ["text-to-video", "image-to-video", "first-last-frame", "reference-to-video", "video-edit", "video-extend"],
      "pricing": {
        "unit": "second",
        "amount": "0.58701",
        "currency": "USD",
        "display": "$0.587 / second",
        "variants": [
          { "resolution": "480p", "amount": "0.2609" },
          { "resolution": "720p", "amount": "0.58701" },
          { "resolution": "1080p", "amount": "1.01608" }
        ]
      }
    }
  ]
}

The list does not include input_schema. Only GET /v1/models/{id} returns the schema.

Model object

Field	Type	Description
`id`	string	Stable id you pass as `model`
`name`	string	Display name
`vendor`	string	Company that makes the model
`category`	string	`image`, `video`, `audio`, `chat` or `tool`
`object`	string	Always `model`
`modes`	array	The model's working modes, described below
`pricing`	object	Price, shape depends on category (below)
`input_schema`	object	Parameters accepted in `input` (media models only, and only in `GET /v1/models/{id}`)
`context_window`, `max_output_tokens`, `anthropic_compatible`	number, number, boolean	Chat models only

The `modes` field

modes lists the modes the model works in. Use it to pick a model before you read input_schema. Example values:

text-to-image, text-to-video - generate from a prompt alone;
image-to-image, image-edit, inpainting - edit an image passed in image_urls;
image-to-video - animate a still passed as the first frame (image_url);
first-last-frame - video between a first and a last frame;
reference-to-video, multi-image-reference - generate from reference images or clips;
video-edit, video-extend - edit or extend an existing clip;
lyrics-to-music - a song from lyrics;
stem-separation, vocal-isolation - split a recording into tracks;
chat - a chat model.

A mode describes what the model can do, it is not a request parameter. You pick it through input fields, for example passing image_url to a model with image-to-video animates the image.

Pricing for media models

Field	Description
`unit`	What one unit is, for example one image or one second of video
`amount`	Price per unit as a decimal string
`currency`	`USD` or `PLN`
`display`	Ready-to-show text, for example `$0.587 / second`
`variants`	Per-unit prices for each value of the parameter the price depends on (for example `resolution`). Empty when there is a single price
`vat_included`	`true` for PLN prices (they include 23% VAT); absent for USD

Pricing for chat models

Field	Description
`input_per_mtok`	Price per 1M input tokens
`output_per_mtok`	Price per 1M output tokens
`currency`	`USD` or `PLN`
`vat_included`	`true` for PLN prices

Prices in PLN include 23% VAT. Current prices for popular models: GPT Image 2.5 $0.0432 per image, FLUX.2 [pro] from $0.0688 per image, Veo 3.1 (Quality) from $2.53 per video, Claude Opus 5.5 $5.40 / $27.00 per 1M tokens.

Get one model

bash

curl https://jantaris.com/v1/models/seedance-2.5

python

model = requests.get("https://jantaris.com/v1/models/seedance-2.5", timeout=30).json()
print(model["input_schema"])

javascript

const model = await (await fetch("https://jantaris.com/v1/models/seedance-2.5")).json();
console.log(model.input_schema);

An unknown id returns 404 not_found.

Input schema

input_schema describes what /v1/generate accepts in input. It follows JSON Schema conventions. An abridged example (read the live schema for real values):

json

{
  "type": "object",
  "properties": {
    "prompt":         { "type": "string" },
    "duration":       { "type": "integer", "minimum": 4, "maximum": 10, "default": 5 },
    "resolution":     { "type": "string", "enum": ["480p", "720p"], "default": "720p" },
    "aspect_ratio":   { "type": "string", "enum": ["16:9", "9:16", "1:1"], "default": "16:9" },
    "image_url":      { "type": "string" },
    "generate_audio": { "type": "boolean", "default": false }
  },
  "required": ["prompt"]
}

Keyword	Meaning
`type`	`string`, `integer`, `number`, `boolean`, `array`
`enum`	Only these values are accepted
`minimum`, `maximum`	Numeric range, inclusive
`default`	Value used when you omit the field
`required`	Fields that must be present

Validation is strict. A field that is not in properties, a wrong type, a value outside enum or out of range returns 422 invalid_request and no task is created, so no funds are held.

Building a valid input in code

python

def build_input(schema: dict, **values) -> dict:
    props = schema.get("properties", {})
    unknown = set(values) - set(props)
    if unknown:
        raise ValueError(f"unknown fields: {unknown}")
    missing = [f for f in schema.get("required", []) if f not in values]
    if missing:
        raise ValueError(f"missing fields: {missing}")
    for name, value in values.items():
        rule = props[name]
        if "enum" in rule and value not in rule["enum"]:
            raise ValueError(f"{name} must be one of {rule['enum']}")
        if "minimum" in rule and value < rule["minimum"]:
            raise ValueError(f"{name} must be >= {rule['minimum']}")
        if "maximum" in rule and value > rule["maximum"]:
            raise ValueError(f"{name} must be <= {rule['maximum']}")
    return values

schema = requests.get("https://jantaris.com/v1/models/seedance-2.5", timeout=30).json()["input_schema"]
payload = {"model": "seedance-2.5", "input": build_input(schema, prompt="Waves at dusk", duration=5)}

The server validates anyway. Checking on your side gives users clear messages before a request leaves your app.

Cost before you call

Media: price per unit times units, for example seconds of video times the per-second price. The exact figure comes back as estimated_cost from /v1/generate, and that amount is held until the task finishes.
Chat: tokens from the usage field times input_per_mtok and output_per_mtok, divided by 1,000,000.

Models

List models

Model object

The modes field

Pricing for media models

Pricing for chat models

Get one model

Input schema

Building a valid input in code

Cost before you call

The `modes` field