Estimate inference price

Viewing v2— current version

POST

/v2/workspaces/{workspace_id}/inferences/estimate

curl --request POST \
  --url https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "base_model_id": "<string>",
  "reference_sets": [],
  "modality": "text",
  "prompt": "<string>",
  "width": 0,
  "height": 0,
  "batch_size": 4,
  "num_inference_steps": 0,
  "guidance_scale": 0,
  "prompt_strength": 0,
  "quality": "low",
  "sharpness": 0,
  "duration_seconds": 0,
  "generate_audio": true,
  "keep_audio": true,
  "fps": 0,
  "video_effects": [],
  "use_ta_pose": true,
  "pose_mode": "A_POSE",
  "include_textures": true,
  "quad_mesh": true,
  "pbr_materials": true,
  "low_poly": true,
  "generate_parts": true,
  "face_limit": 0,
  "stability": 0,
  "use_speaker_boost": true,
  "similarity_boost": 0,
  "style_exaggeration": 0,
  "speed": 0,
  "upscale_ratio": 0,
  "creativity": 0,
  "resemblance": 0,
  "vectorize": true,
  "remove_background": true,
  "reframe": true,
  "refill": true,
  "guidance_files": []
}'

import requests

url = "https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate"

payload = {
    "base_model_id": "<string>",
    "reference_sets": [],
    "modality": "text",
    "prompt": "<string>",
    "width": 0,
    "height": 0,
    "batch_size": 4,
    "num_inference_steps": 0,
    "guidance_scale": 0,
    "prompt_strength": 0,
    "quality": "low",
    "sharpness": 0,
    "duration_seconds": 0,
    "generate_audio": True,
    "keep_audio": True,
    "fps": 0,
    "video_effects": [],
    "use_ta_pose": True,
    "pose_mode": "A_POSE",
    "include_textures": True,
    "quad_mesh": True,
    "pbr_materials": True,
    "low_poly": True,
    "generate_parts": True,
    "face_limit": 0,
    "stability": 0,
    "use_speaker_boost": True,
    "similarity_boost": 0,
    "style_exaggeration": 0,
    "speed": 0,
    "upscale_ratio": 0,
    "creativity": 0,
    "resemblance": 0,
    "vectorize": True,
    "remove_background": True,
    "reframe": True,
    "refill": True,
    "guidance_files": []
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())

const url = 'https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"base_model_id":"<string>","reference_sets":[],"modality":"text","prompt":"<string>","width":0,"height":0,"batch_size":4,"num_inference_steps":0,"guidance_scale":0,"prompt_strength":0,"quality":"low","sharpness":0,"duration_seconds":0,"generate_audio":true,"keep_audio":true,"fps":0,"video_effects":[],"use_ta_pose":true,"pose_mode":"A_POSE","include_textures":true,"quad_mesh":true,"pbr_materials":true,"low_poly":true,"generate_parts":true,"face_limit":0,"stability":0,"use_speaker_boost":true,"similarity_boost":0,"style_exaggeration":0,"speed":0,"upscale_ratio":0,"creativity":0,"resemblance":0,"vectorize":true,"remove_background":true,"reframe":true,"refill":true,"guidance_files":[]}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

package main

import (
  "fmt"
  "strings"
  "net/http"
  "io"
)

func main() {

  url := "https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate"

  payload := strings.NewReader("{\n  \"base_model_id\": \"<string>\",\n  \"reference_sets\": [],\n  \"modality\": \"text\",\n  \"prompt\": \"<string>\",\n  \"width\": 0,\n  \"height\": 0,\n  \"batch_size\": 4,\n  \"num_inference_steps\": 0,\n  \"guidance_scale\": 0,\n  \"prompt_strength\": 0,\n  \"quality\": \"low\",\n  \"sharpness\": 0,\n  \"duration_seconds\": 0,\n  \"generate_audio\": true,\n  \"keep_audio\": true,\n  \"fps\": 0,\n  \"video_effects\": [],\n  \"use_ta_pose\": true,\n  \"pose_mode\": \"A_POSE\",\n  \"include_textures\": true,\n  \"quad_mesh\": true,\n  \"pbr_materials\": true,\n  \"low_poly\": true,\n  \"generate_parts\": true,\n  \"face_limit\": 0,\n  \"stability\": 0,\n  \"use_speaker_boost\": true,\n  \"similarity_boost\": 0,\n  \"style_exaggeration\": 0,\n  \"speed\": 0,\n  \"upscale_ratio\": 0,\n  \"creativity\": 0,\n  \"resemblance\": 0,\n  \"vectorize\": true,\n  \"remove_background\": true,\n  \"reframe\": true,\n  \"refill\": true,\n  \"guidance_files\": []\n}")

  req, _ := http.NewRequest("POST", url, payload)

  req.Header.Add("Authorization", "Bearer <token>")
  req.Header.Add("Content-Type", "application/json")

  res, _ := http.DefaultClient.Do(req)

  defer res.Body.Close()
  body, _ := io.ReadAll(res.Body)

  fmt.Println(res)
  fmt.Println(string(body))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'base_model_id' => '<string>',
    'reference_sets' => [

    ],
    'modality' => 'text',
    'prompt' => '<string>',
    'width' => 0,
    'height' => 0,
    'batch_size' => 4,
    'num_inference_steps' => 0,
    'guidance_scale' => 0,
    'prompt_strength' => 0,
    'quality' => 'low',
    'sharpness' => 0,
    'duration_seconds' => 0,
    'generate_audio' => null,
    'keep_audio' => null,
    'fps' => 0,
    'video_effects' => [

    ],
    'use_ta_pose' => null,
    'pose_mode' => 'A_POSE',
    'include_textures' => null,
    'quad_mesh' => null,
    'pbr_materials' => null,
    'low_poly' => null,
    'generate_parts' => null,
    'face_limit' => 0,
    'stability' => 0,
    'use_speaker_boost' => null,
    'similarity_boost' => 0,
    'style_exaggeration' => 0,
    'speed' => 0,
    'upscale_ratio' => 0,
    'creativity' => 0,
    'resemblance' => 0,
    'vectorize' => null,
    'remove_background' => null,
    'reframe' => null,
    'refill' => null,
    'guidance_files' => [

    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\n  \"base_model_id\": \"<string>\",\n  \"reference_sets\": [],\n  \"modality\": \"text\",\n  \"prompt\": \"<string>\",\n  \"width\": 0,\n  \"height\": 0,\n  \"batch_size\": 4,\n  \"num_inference_steps\": 0,\n  \"guidance_scale\": 0,\n  \"prompt_strength\": 0,\n  \"quality\": \"low\",\n  \"sharpness\": 0,\n  \"duration_seconds\": 0,\n  \"generate_audio\": true,\n  \"keep_audio\": true,\n  \"fps\": 0,\n  \"video_effects\": [],\n  \"use_ta_pose\": true,\n  \"pose_mode\": \"A_POSE\",\n  \"include_textures\": true,\n  \"quad_mesh\": true,\n  \"pbr_materials\": true,\n  \"low_poly\": true,\n  \"generate_parts\": true,\n  \"face_limit\": 0,\n  \"stability\": 0,\n  \"use_speaker_boost\": true,\n  \"similarity_boost\": 0,\n  \"style_exaggeration\": 0,\n  \"speed\": 0,\n  \"upscale_ratio\": 0,\n  \"creativity\": 0,\n  \"resemblance\": 0,\n  \"vectorize\": true,\n  \"remove_background\": true,\n  \"reframe\": true,\n  \"refill\": true,\n  \"guidance_files\": []\n}");
Request request = new Request.Builder()
  .url("https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate")
  .post(body)
  .addHeader("Authorization", "Bearer <token>")
  .addHeader("Content-Type", "application/json")
  .build();

Response response = client.newCall(request).execute();

require 'uri'
require 'net/http'

url = URI("https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"base_model_id\": \"<string>\",\n  \"reference_sets\": [],\n  \"modality\": \"text\",\n  \"prompt\": \"<string>\",\n  \"width\": 0,\n  \"height\": 0,\n  \"batch_size\": 4,\n  \"num_inference_steps\": 0,\n  \"guidance_scale\": 0,\n  \"prompt_strength\": 0,\n  \"quality\": \"low\",\n  \"sharpness\": 0,\n  \"duration_seconds\": 0,\n  \"generate_audio\": true,\n  \"keep_audio\": true,\n  \"fps\": 0,\n  \"video_effects\": [],\n  \"use_ta_pose\": true,\n  \"pose_mode\": \"A_POSE\",\n  \"include_textures\": true,\n  \"quad_mesh\": true,\n  \"pbr_materials\": true,\n  \"low_poly\": true,\n  \"generate_parts\": true,\n  \"face_limit\": 0,\n  \"stability\": 0,\n  \"use_speaker_boost\": true,\n  \"similarity_boost\": 0,\n  \"style_exaggeration\": 0,\n  \"speed\": 0,\n  \"upscale_ratio\": 0,\n  \"creativity\": 0,\n  \"resemblance\": 0,\n  \"vectorize\": true,\n  \"remove_background\": true,\n  \"reframe\": true,\n  \"refill\": true,\n  \"guidance_files\": []\n}"

response = http.request(request)
puts response.read_body

var client = new RestClient("https://api.app.layer.ai/api/v2/workspaces/:workspace_id/inferences/estimate");
var request = new RestRequest("", Method.Post);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"base_model_id\": \"<string>\",\n  \"reference_sets\": [],\n  \"modality\": \"text\",\n  \"prompt\": \"<string>\",\n  \"width\": 0,\n  \"height\": 0,\n  \"batch_size\": 4,\n  \"num_inference_steps\": 0,\n  \"guidance_scale\": 0,\n  \"prompt_strength\": 0,\n  \"quality\": \"low\",\n  \"sharpness\": 0,\n  \"duration_seconds\": 0,\n  \"generate_audio\": true,\n  \"keep_audio\": true,\n  \"fps\": 0,\n  \"video_effects\": [],\n  \"use_ta_pose\": true,\n  \"pose_mode\": \"A_POSE\",\n  \"include_textures\": true,\n  \"quad_mesh\": true,\n  \"pbr_materials\": true,\n  \"low_poly\": true,\n  \"generate_parts\": true,\n  \"face_limit\": 0,\n  \"stability\": 0,\n  \"use_speaker_boost\": true,\n  \"similarity_boost\": 0,\n  \"style_exaggeration\": 0,\n  \"speed\": 0,\n  \"upscale_ratio\": 0,\n  \"creativity\": 0,\n  \"resemblance\": 0,\n  \"vectorize\": true,\n  \"remove_background\": true,\n  \"reframe\": true,\n  \"refill\": true,\n  \"guidance_files\": []\n}", ParameterType.RequestBody);
var response = client.Execute(request);

Changed in v2. This endpoint’s contract differs from v1. See the v2 migration guide for the request and response changes before you switch.

Estimate the Creative Units cost of an inference with given parameters. Prices through the same reference-set translation and model selection as the execute endpoint, so the price matches what execution charges for identical inputs.

Reference-set errors: REFERENCE_SET_NOT_FOUND (404 — unknown, deleted, or outside this workspace’s reach), NO_COMPATIBLE_MODEL (422 — no enabled base model can apply these sets), REFERENCE_SET_REQUIRED (422 — the chosen model needs an applicable set), REFERENCE_SET_CONFLICT (422 — two sets supply the same singular adapter), and INPUT_FILE_REQUIRED (422 — the sets select an edit-only model with no asset to edit).

Authorizations

bearerAuth

Parameters

Path Parameters

workspace_id

required

Workspace Id

Id of the workspace that owns the resource.

string format: uuid

Id of the workspace that owns the resource.

Request Body^required

application/json

EstimateInferencePriceV2Request

REST request body for estimating inference price. workspace_id comes from path.

object

base_model_id

Any of:

string
null

string

reference_sets

Reference Sets

Reference sets to apply, up to 10.

Array<object>

default: <= 10 items

InferenceReferenceSetInput

object

set_id

required

Set Id

Reference set ID from GET /v2/workspaces/{workspace_id}/reference-sets.

string format: uuid

weight

Weight

Weight for the set’s LoRA adapter when one applies. Ignored for sets applied as reference images or prompt text.

number

default: 1 <= 2

modality

Any of:

Modality
null

Modality

string

Allowed values: text image audio video three_d playable

prompt

Any of:

string
null

string

<= 100000 characters

width

Any of:

integer
null

integer

> 0

height

Any of:

integer
null

integer

> 0

batch_size

Batch Size

Number of outputs (1-16).

integer

default: 4 >= 1 <= 16

num_inference_steps

Any of:

integer
null

integer

> 0

guidance_scale

Any of:

number
null

number

prompt_strength

Any of:

number
null

number

<= 1

quality

Any of:

string
null

string

Allowed values: low medium high

sharpness

Any of:

number
null

number

duration_seconds

Any of:

number
null

number

> 0

generate_audio

Any of:

boolean
null

boolean

keep_audio

Any of:

boolean
null

boolean

fps

Any of:

integer
null

integer

> 0

video_effects

Video Effects

Video effects to apply.

Array<object>

default:

ForgeVideoEffectInput

object

type

required

VideoEffectType

Video effect type. See model capabilities for supported effects per model.

string

Allowed values: general orbit_360 action_run agent_reveal arc arc_left baseball_kick basketball_dunks boxing buckle_up building_explosion bullet_time car_chasing car_explosion car_grip catch catwalk crane_down crane_over_the_head crane_up crash_zoom_in crash_zoom_out dirty_lens disintegration dolly_in dolly_left dolly_out dolly_right dolly_zoom_in dolly_zoom_out double_dolly downhill_pov dutch_angle eyes_in face_punch fisheye flying focus_change fpv_drone glam handheld head_tracking hyperlapse invisible jib_down jib_up kiss lazy_susan lens_crack lens_flare levitation low_shutter melting moonwalk_left moonwalk_right mouth_in object_pov overhead push_to_glass rap_flex robo_arm set_on_fire skateboard_glide skateboarding skateboard_kickflip skateboard_ollie skate_cruise ski_carving ski_powder snorricam snowboard_carving snowboard_powder soul_jump static super_dolly_in super_dolly_out tentacles through_object_in through_object_out thunder_god tilt_down tilt_up timelapse_human timelapse_landscape turning_metal whip_pan wiggle wind_to_face yoyo_zoom zoom_in zoom_out

weight

Any of:

number
null

number

<= 100

use_ta_pose

Any of:

boolean
null

boolean

pose_mode

Any of:

PoseMode
null

PoseMode

Canonical rest pose a character-mesh model is asked to generate in. A_POSE places the arms angled down at roughly 45°; T_POSE holds them straight out to the sides. Only meaningful for models that advertise the pose_modes capability (e.g. Meshy V7).

Deliberately a light top-level module (like base_model_id), NOT under pkg.models.inference: the Blueprint definition layer registers this as a BlueprintType and migrates legacy node ports, and must do so without pulling in the heavy pkg.models.inference package, which would perturb the Temporal workflow-sandbox import graph and split pydantic class identity.

string

Allowed values: A_POSE T_POSE

include_textures

Any of:

boolean
null

boolean

quad_mesh

Any of:

boolean
null

boolean

pbr_materials

Any of:

boolean
null

boolean

low_poly

Any of:

boolean
null

boolean

generate_parts

Any of:

boolean
null

boolean

face_limit

Any of:

integer
null

integer

> 0

stability

Any of:

number
null

number

<= 1

use_speaker_boost

Any of:

boolean
null

boolean

similarity_boost

Any of:

number
null

number

<= 1

style_exaggeration

Any of:

number
null

number

<= 1

speed

Any of:

number
null

number

> 0

upscale_ratio

Any of:

number
null

number

creativity

Any of:

number
null

number

resemblance

Any of:

number
null

number

vectorize

Any of:

boolean
null

boolean

remove_background

Any of:

boolean
null

boolean

reframe

Any of:

boolean
null

boolean

refill

Any of:

boolean
null

boolean

guidance_files

Guidance Files

Reference images/files to guide generation.

Array<object>

default: <= 20 items

ForgeGuidanceFileInput

object

file_id

required

File Id

File ID of an uploaded file.

string format: uuid

type

required

GuidanceFileType

Guidance type. See model capabilities for supported types per model.

string

Allowed values: init_image reference_image scribble color_sketch pose depth canny softedge_hed segmentation lineart face ip_adapter first_frame last_frame init_video reference_video init_mesh texture_image element_frontal_image element_reference_image element_video init_audio reference_audio

weight

Any of:

number
null

number

<= 1

Responses

200

Successful Response

application/json

EstimateInferencePriceV2Output

object

estimated_price_creative_units

required

Estimated Price Creative Units

Total estimated Creative Units price for this run.

number

workspace_balance_creative_units

required

Workspace Balance Creative Units

Usable Creative Units balance (total balance minus reserved by in-progress generations).

number

estimated_remaining_balance_creative_units

required

Estimated Remaining Balance Creative Units

Usable balance after subtracting the estimated price. Can be negative.

number

has_sufficient_creative_units

required

Has Sufficient Creative Units

Whether the workspace has enough available Creative Units to cover the estimated price.

boolean

base_model_id

required

Base Model Id

Base model this price refers to, resolved or auto-picked.

string

auto_picked

required

Auto Picked

True when no base_model_id was supplied — the base model was selected from the reference sets.

boolean

reference_set_contributions

Reference Set Contributions

Per-set summary of what each reference set would contribute to this run.

Array<object>

default:

ForgeReferenceSetContribution

object

set_id

Any of:

string
null

string format: uuid

lora_applied

Lora Applied

True when a LoRA finetune was applied for this set.

boolean

animation_applied

Animation Applied

True when an animation (Meshy rigging action) finetune was applied for this set.

boolean

voice_applied

Voice Applied

True when a voice (ElevenLabs) finetune was applied for this set.

boolean

mapped_asset_count

Mapped Asset Count

Number of assets successfully mapped to guidance inputs.

integer

prompt_fallback_applied

Prompt Fallback Applied

True when the set fell back to prompt-only representation.

boolean

lora_available_but_incompatible

Lora Available But Incompatible

True when SBMC has a LoRA for this set on another base model but not the one used.

boolean

skipped_not_applicable

Skipped Not Applicable

True when the set isn’t applicable to the chosen model (its modality / applicable base models exclude it) so no LoRA or assets were applied.

boolean

reference_sets_degraded

Reference Sets Degraded

True when at least one attached reference set would not meaningfully contribute on the selected model.

boolean

reference_sets_warning

Any of:

string
null

string

Example

{
  "reference_set_contributions": [],
  "reference_sets_degraded": false
}

401

Unauthenticated — missing or invalid Bearer token.

application/problem+json

object

type

required

string

title

required

string

status

required

integer

detail

required

string

Example

{
  "type": "https://api.layer.ai/errors/ERROR_CODE",
  "title": "Error Title",
  "status": 400,
  "detail": "Human-readable description."
}

403

Forbidden — insufficient permissions.

application/problem+json

object

type

required

string

title

required

string

status

required

integer

detail

required

string

Example

{
  "type": "https://api.layer.ai/errors/ERROR_CODE",
  "title": "Error Title",
  "status": 400,
  "detail": "Human-readable description."
}

404

Resource not found.

application/problem+json

object

type

required

string

title

required

string

status

required

integer

detail

required

string

Example

{
  "type": "https://api.layer.ai/errors/ERROR_CODE",
  "title": "Error Title",
  "status": 400,
  "detail": "Human-readable description."
}

422

Invalid input parameters.

application/problem+json

object

type

required

string

title

required

string

status

required

integer

detail

required

string

Example

{
  "type": "https://api.layer.ai/errors/ERROR_CODE",
  "title": "Error Title",
  "status": 400,
  "detail": "Human-readable description."
}

429

Rate limited — too many concurrent requests.

application/problem+json

object

type

required

string

title

required

string

status

required

integer

detail

required

string

Example

{
  "type": "https://api.layer.ai/errors/ERROR_CODE",
  "title": "Error Title",
  "status": 400,
  "detail": "Human-readable description."
}

500

Internal server error.

application/problem+json

object

type

required

string

title

required

string

status

required

integer

detail

required

string

Example

{
  "type": "https://api.layer.ai/errors/ERROR_CODE",
  "title": "Error Title",
  "status": 400,
  "detail": "Human-readable description."
}

Estimate inference price

Authorizations

Parameters

Path Parameters

Request Bodyrequired

Responses

200

Example

401

Example

403

Example

404

Example

422

Example

429

Example

500

Example

Request Body^required