# lumv.app API guide for LLMs and automated agents > lumv.app generates images, video, 3D models, speech, sound effects and music, and serves text chat models. > Agents use a personal API key. Generations are asynchronous jobs (estimate, start, poll, download) at > /v1/generations; text models use the OpenAI-compatible /v1/chat/completions and /v1/responses. > Money is counted in credits: 1 credit = 1 RUB = 100 kopecks. Every *Cents field is an integer number of kopecks. ## Access - Origin: https://lumv.app. API base URL, also for OpenAI SDKs: https://lumv.app/v1. - The user signs in at https://lumv.app, funds a wallet and creates a personal key at https://lumv.app/account/api/keys. The full key (sk-lumv-...) is shown once. A key can have an expiry date and a monthly spending limit; a user can hold up to 20 active keys. - Send Authorization: Bearer on every protected request, including file downloads. /v1 ignores cookies. - Read the key from a secret store or the LUMV_API_KEY environment variable. Never write it into code, URLs, repositories, messages or logs, and never send it to any host other than lumv.app. - Public without a key: GET /v1/generation-models, GET /v1/generation-models/:id, /llms.txt, /llms-full.txt and the /docs/api pages. Every other /v1 route requires the key, including GET /v1/models. - The user sees every API request and its cost at https://lumv.app/account/api/usage. ## Endpoints | Method | Path | Purpose | | --- | --- | --- | | GET | /v1/generation-models | Public list of enabled generation models: fields, scenarios, examples | | GET | /v1/generation-models/:id | One generation model contract (404 model_not_found if disabled or unknown) | | POST | /v1/generations/estimate | Free price quote for a request body; nothing is charged or created | | POST | /v1/generations | Start an asynchronous generation: 202 { generation } | | GET | /v1/generations/:id | Status and results of your own generation | | GET, HEAD | /v1/generations/:id/assets/:asset | Download a result file (Range; ?download=1 for an attachment) | | POST | /v1/uploads | Create an upload session for a new input file | | PUT | /v1/uploads/:id/content | Send the file bytes with X-Upload-Token | | POST | /v1/uploads/:id/complete | Finish the upload and start validation | | DELETE | /v1/uploads/:id | Cancel an unfinished upload | | GET | /v1/assets/:id | State of an owned asset | | GET, HEAD | /v1/assets/:id/content | Content of an owned asset (Range; ?role=thumbnail for image previews) | | GET | /v1/projects | Project folders you can store generations in (projectId) | | GET | /v1/models, /v1/models/:id | OpenAI-compatible list of text models | | POST | /v1/chat/completions | OpenAI Chat Completions for text models | | POST | /v1/responses | OpenAI Responses for text models | | GET, DELETE | /v1/responses/:id | Read or delete a stored response | | GET | /v1/responses/:id/input_items | Input items of a stored response | ## Choosing a generation model - Read GET /v1/generation-models (or the live catalog at the end of /llms-full.txt) before a task. Never invent model IDs, field names or option values. - A model has id (send it as "model"), name, description, category, endpoint ("/v1/generations"), basePriceCents (indicative starting price), fields and scenarios. name, description and field labels are UI text and may be Russian; always use the machine names. - Field keys: name, label, description, type, required, defaultValue, options [{ value, label }], minimum, maximum, step, maximumLength, accept, multiple, maximumItems, requires, visibleWhen { field, equals }, valueType, routingOnly, advanced, scenarios. - Generation models are called only through POST /v1/generations, never through /chat/completions, /responses or /images/generations. Text models from GET /v1/models are called only through the OpenAI-compatible endpoints. ## Request body ```json { "model": "MODEL_ID_FROM_CATALOG", "values": { "prompt": "A red fox in fresh snow, golden hour" }, "inputAssets": [{ "fieldName": "FILE_FIELD_NAME", "assetId": "READY_ASSET_ID", "position": 0 }], "projectId": "OPTIONAL_PROJECT_ID" } ``` - Only model, values, inputAssets and projectId are accepted at the top level; any other key returns 400. - values contains only field names of that model; unknown names, null and wrong JSON types return 400. - Types: text, textarea and dimensions are JSON strings (dimensions such as "1024x1024" or an option value); number is a JSON number; boolean is true or false; select is one of options[].value as a string, or as a JSON number when valueType is "number"; json is a JSON object or array, or a string containing JSON. Omitted fields use defaultValue. - File fields (type "file") never go into values. Pass them in inputAssets: fieldName is the file field, assetId is an owned asset with status "ready", position is a 0-based index (0..maximumItems-1 for multiple fields). At most 100 references per request. URLs and base64 data are rejected. - requires: the field may be sent only together with the named field. visibleWhen: the field applies only while another field equals the given value. required, maximumLength, minimum, maximum, step, options and maximumItems are enforced; contract violations return 422 with code invalid_model_input. ## Scenarios A model can have several scenarios. The server picks one from your request: scenarios are checked in the listed order and the first matching condition wins; the scenario without a condition is the fallback. Conditions: file_present (a file is attached to that field), truthy (the field is true, "true", "on" or a positive number), equals (the field equals value exactly). A field with a scenarios list exists only in those scenarios, and its required flag applies only there. Scenario limits override a field's minimum and maximum. Every scenario has a ready "example" request in the JSON contract. ## Estimate POST /v1/generations/estimate takes the same body you will start (projectId is ignored here): ```json { "model": "MODEL_ID", "costCents": 1500, "currency": "RUB", "charged": false, "billing": { "wallet": "personal", "unlimited": false, "chargeCents": 1500, "keyBinding": "personal" } } ``` - costCents is the catalog price of this exact request in kopecks (1500 = 15 credits). - billing is the wallet that would pay: wallet "personal" or "team" (then also teamName); unlimited is true for an unlimited team; chargeCents is what would actually be debited (0 for unlimited teams); providerEstimateUsdMicros (unlimited teams only) is the expected provider cost in millionths of a US dollar. keyBinding is the key's wallet mode: "personal", "team" or "account" (follows the wallet selected in the web app). - The estimate validates values and inputAssets. It does not check the balance, reserve money, check projectId, check provider availability or create a job. Prices can change between estimate and start. - Before paid runs, agree on the total budget and the number of runs with the user. A successful test of one item is not permission to run ten. Treat the key's monthly limit as a hard cap. ## Start and poll - POST /v1/generations reserves the price from the wallet and returns HTTP 202, Retry-After: 3 and { "generation" }. - GET /v1/generations/:id returns { "generation" }. status: uploading, queued, processing (keep polling every 3-5 seconds, back off on temporary errors), completed (results ready) or failed (read error; the reserve is returned automatically and refunded becomes 1). - A client timeout does not cancel the job: store generation.id and resume polling later. Do not blindly retry a failed job; read error and check the budget first. Other users' generations return 404. - Generation fields: id, object ("generation"), status, error, createdAt and updatedAt (Unix ms), modelId (catalog id), modelName, category, scenarioName, parameters (display summary), prompt (main text instruction or null), reuseValues (non-file values for repeating the request), costCents (charged kopecks, 0 for unlimited teams), refunded, billingMode ("personal", "team" or "team_unlimited"), usageUsdMicros (provider cost in micro-USD for team_unlimited, otherwise null), projectId, projectName, assets, modelFormats, inputAssets, previewUrl, viewerUrl, viewerFormat, modelUrl, downloadUrl and textOutput. ## Results and downloads - assets[]: id, url, downloadUrl, contentType, fileName, fileSize, mediaAssetId. url and downloadUrl are relative (/v1/generations/:id/assets/:asset, downloadUrl adds ?download=1). Prefix https://lumv.app and send the same Bearer header. GET, HEAD and Range requests are supported. - previewUrl is the main preview; viewerUrl, modelUrl and downloadUrl point to the main 3D file (viewerFormat "gltf" or "fbx"); textOutput holds text results; inputAssets[] lists the files used as inputs. - modelFormats[] (3D results only): format ("glb", "gltf", "fbx", "obj", "usdz" or "stl"), origin ("original" from the provider or "converted" by lumv), status ("ready", "processing" or "failed"), downloadUrl, fileName, fileSize. The original GLB is ready with the generation; FBX (textures embedded) and OBJ (ZIP with OBJ, MTL and textures) are converted in the background, usually within a minute: keep polling GET /v1/generations/:id while a format is "processing", then download /v1/generations/:id/exports/:format with the same Bearer header. - Never hand these URLs to a model or a third party; reuse results by mediaAssetId instead. ## Chaining results mediaAssetId is the owned library asset of a result. It can be null briefly while the result is being saved: poll the generation until it appears, then GET /v1/assets/:mediaAssetId until asset.status is "ready", and pass it as inputAssets[].assetId to the next model. Owned images, videos and audio can be reused when the field's accept list allows their type. If an asset does not become ready in a reasonable time, report it and keep the generation id. Example task "10 images -> 10 3D models": 1. Pick an image model and a 3D model with an image file field from the catalog. 2. Fix parameters and the budget of the whole chain; estimate each step before starting it. 3. Keep a manifest for the 10 pairs: prompt, idempotency keys, generation IDs, asset IDs, cost, state. Save it after every step so the run can resume after an interruption. 4. Generate the image of a pair; wait for completed and a ready image asset. 5. Pass that assetId to the 3D model through inputAssets. For Tripo, for example, choose generation_mode h31_image or p1_image and fieldName image_url; take the exact limits from the current schema. 6. Wait for the completed 3D model, download it and mark the pair done. 7. Continue with the other pairs. Keep at most 4 unfinished requests per key; sequential runs are simplest. ## Uploading new input files 1. POST /v1/uploads with { "profile": "reference_image", "fileName": "input.png", "contentType": "image/png", "size": BYTES } and an Idempotency-Key header (required, 8-128 characters from A-Z a-z 0-9 . _ : -). The same key and declaration return the same session. Response 201 (200 on replay): { "upload": { id, assetId, state, uploadUrl, leaseToken, maximumBytes, expiresAt } }. 2. PUT https://lumv.app + uploadUrl with the raw bytes and the headers Authorization, Content-Type and X-Upload-Token: . Never send more than maximumBytes. 3. POST /v1/uploads/:id/complete returns 202 { assetId, status: "pending" }. 4. GET /v1/assets/:assetId until asset.status is "ready" ("pending" and "validating" mean wait; "rejected" means stop and report). - Profiles for generation inputs: reference_image (JPEG, PNG or WebP up to 10 MiB) and image_mask (PNG up to 10 MiB, same size as the source image; for mask fields). chat_pdf and chat_text are web chat attachments; the text API accepts text content only. Uploading your own video or audio is not supported; reuse generated results by ID. - Upload sessions expire after 1 hour; DELETE /v1/uploads/:id cancels an unfinished one. Account quotas (by default 2 active upload sessions, 10 files awaiting validation, 250 MiB per day, 1 GiB of storage) return 429 when exceeded. ## Projects projectId (POST /v1/generations only) stores the result in a project folder of the web workspace: your own project, or a team-shared project where you have contribute access. A view-only project returns 403; a missing or invisible one returns 404. GET /v1/projects lists the folders you can store results in: { "object": "list", "data": [{ "id", "object": "project", "name", "color", "team" (team name or null), "owned" }] }. The id is also in the project page URL (https://lumv.app/projects/). The generation then reports projectId and projectName. projectId is part of the idempotency fingerprint. Text endpoints do not accept projectId. ## Wallets and billing - Every API key is bound to a wallet when it is created (the user can change it later in /account/api/keys): the personal balance, one team the user belongs to, or "account" (follow the wallet selected in the web app's account settings or header switcher at request time; keys created before key binding use this mode). The estimate's billing block shows which wallet will pay and keyBinding shows the key's mode. - A key bound to a team the user has left, or to an archived team, is never silently switched to another wallet: estimates and new requests return 403 with code wallet_unavailable until the user picks another wallet. - Personal and prepaid team wallets: the price is reserved at start; refunds and adjustments return to the same wallet. Insufficient funds return 402 (for a team wallet the message names the team). - Unlimited teams: nothing is debited. costCents and billing.chargeCents are 0, billingMode is "team_unlimited", and usageUsdMicros or providerEstimateUsdMicros report the provider cost (1 USD = 1,000,000 micros). - A team that uses its own provider keys reaches only the models those providers serve; other models fail at start with 503 (no suitable connection for the team). Estimates do not detect this. - The key's monthly limit counts reserves of the current UTC calendar month (failed requests excluded); a request that would exceed it returns 402. - Text models are billed by tokens: the start reserves the maximum (context, max tokens and the reasoning reserve); the final charge follows the reported usage and never exceeds the reserve. ## Idempotency and retries - Send a unique Idempotency-Key header (1-128 printable ASCII characters, no spaces) with every logical POST /v1/generations, /v1/chat/completions and /v1/responses request. Keys are scoped to the API key. - The same key with the same body (including projectId) returns the original job instead of charging again; the same key with a different body returns 409. - Save the key and the body before sending. After a timeout or a network error, retry with the same key and body. Never change the key while the outcome is unknown, or the request may run and be charged twice. - Retry only 429, 503, 504 and network errors, a limited number of times with exponential backoff, and honor Retry-After when present. Never retry in an endless loop. ## Limits - 4 unfinished requests per key, generations and text requests combined; more return 429 until one finishes. - JSON bodies up to 6,000,000 bytes (the gateway rejects anything over 8 MiB); larger bodies return 413. - inputAssets: up to 100 references per request, and each field's maximumItems. - Gateway rate limit of about 100 requests per second per IP address (429). - Upload content: the profile maximum (10 MiB for images); the gateway accepts at most 20 MiB per PUT. - Text requests: 1-1000 messages, up to 200,000 characters per text part, up to 32 tools, max tokens from 1 to the model's output limit (Gemini 4 Argon: 1,000,000; default 4096). A non-streaming request waits up to 14 minutes (2 hours when max tokens exceed 128,000) and then returns 504; repeat it with the same Idempotency-Key to get the same result. ## Errors Errors look like { "error": { "message", "type", "param": null, "code" } }. message is human-readable and usually in Russian, so branch on the HTTP status and code. type is "authentication_error" for 401 and "invalid_request_error" otherwise; code is null, invalid_request_error or one of model_not_found, not_found, response_not_found, invalid_model_input, invalid_project, wallet_unavailable, rate_limit_exceeded. The gateway can answer 413 or 429 without a JSON body. | Status | Meaning | What to do | | --- | --- | --- | | 400 | Invalid JSON, unknown top-level key or field, wrong value type, file in values, bad Idempotency-Key, unsupported OpenAI parameter | Fix the request; do not retry unchanged | | 401 | Missing, revoked or expired key | Stop and ask the user for a valid key | | 402 | Wallet balance too low or the key's monthly limit reached | Stop and tell the user | | 403 | The project does not accept new results from you (invalid_project), or the key's team wallet is no longer available (wallet_unavailable) | Drop projectId, or ask the user to choose another wallet for the key | | 404 | Model, generation, asset, upload, project or stored response is missing or not yours | Check the IDs | | 408 | Upload body was not received in time | Repeat the PUT | | 409 | Idempotency-Key reused with a different body | Resend the original body, or use a new key for a new task | | 413 | Body or file too large | Make it smaller | | 415 | Unsupported upload profile or file format | Use a supported profile and type | | 416 | Invalid Range header | Fix the range | | 422 | values break the model contract (REQUIRED, INVALID_*, OUT_OF_RANGE, TEXT_TOO_LONG, TOO_MANY_FILES, REQUIRES_FIELD) | Fix values against the schema | | 429 | 4 unfinished requests on the key, gateway rate limit or upload quota | Wait for running jobs, then back off | | 502 | The text model failed to answer (the reserve is returned) | Retry later with a new Idempotency-Key | | 503 | Temporary failure, no available provider (also: no suitable connection for the team), uploads disabled | Limited retries with the same key | | 504 | A text request timed out while waiting | Retry with the same Idempotency-Key | ## OpenAI-compatible text API Base URL https://lumv.app/v1, the lumv key as the API key, model IDs from GET /v1/models (or the text models at the end of /llms-full.txt). GET /v1/models returns { "object": "list", "data": [{ "id", "object": "model", "created": 0, "owned_by": "lumv" }] }. Text only: image, audio and file inputs, response_format and built-in tools are not supported. ### POST /v1/chat/completions - Accepted: model, messages (roles system, developer, user, assistant, tool; content is a string or an array of { "type": "text", "text" } parts), max_tokens or max_completion_tokens, temperature (0-2), top_p (above 0, up to 1), tools, tool_choice ("none", "auto", "required" or { "type": "function", "function": { "name" } }), parallel_tool_calls, reasoning_effort, stream, stream_options.include_usage and n (1 only). response_format, audio and modalities return 400; other OpenAI parameters are ignored. - Response: chat.completion with choices[0].message (content and/or tool_calls), finish_reason ("stop", "length" or "tool_calls") and usage (prompt_tokens, completion_tokens, total_tokens, prompt_tokens_details.cached_tokens). - stream: true returns text/event-stream with chat.completion.chunk objects, ": keep-alive" comments every 10 seconds, tool_calls in one chunk at the end, a final usage chunk with empty choices when include_usage is true, errors as data: { "error" } and the terminator data: [DONE]. ### POST /v1/responses - Accepted keys: model, input (a string, or items: messages with roles system, developer, user or assistant and string or input_text/output_text content; function_call; function_call_output; reasoning), instructions, previous_response_id, max_output_tokens, stream, store (default true), tools, tool_choice, temperature, top_p, parallel_tool_calls, reasoning, text ({ "format": { "type": "text" } } and verbosity low, medium or high), metadata (up to 16 string pairs; keys up to 64 and values up to 512 characters), background (false only), truncation ("disabled" only), stream_options ({ "include_obfuscation": false } only), prompt_cache_key and include (["reasoning.encrypted_content"] only). Any other key returns 400. - Response: object "response" with status ("completed", "failed" or "in_progress"), output items (message with output_text, function_call with call_id, name and arguments, reasoning with summary_text) and usage (input_tokens, output_tokens, input_tokens_details.cached_tokens, output_tokens_details.reasoning_tokens). - Stored responses (store true): GET /v1/responses/:id, GET /v1/responses/:id/input_items (a list, has_more false) and DELETE /v1/responses/:id ({ "id", "object": "response.deleted", "deleted": true }). previous_response_id continues a completed stored response; earlier system and developer messages are not carried over, so send instructions again. - stream: true emits events with type and sequence_number: response.created, response.in_progress, response.output_item.added, response.content_part.added, response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done, response.function_call_arguments.delta, response.function_call_arguments.done, response.completed, response.failed and error. ### Function tools Declare up to 32 tools of type "function" (name matching [a-zA-Z0-9_-]{1,64}, optional description, JSON Schema parameters and strict). Chat Completions nests them as { "type": "function", "function": { ... } }; Responses uses the flat { "type": "function", "name", ... } form. When the model calls a tool, run it yourself: send back the assistant message with tool_calls and then { "role": "tool", "tool_call_id", "content" } messages, or function_call_output items with call_id in Responses. lumv never executes your tools. ### Reasoning effort reasoning_effort (Chat Completions) or reasoning.effort (Responses) accepts none, minimal, low, medium, high, xhigh, max or ultra, but only the values a model lists (reasoning_effort in the text model catalog); other values return 400. Higher effort increases the reserved price. Responses also accept reasoning.summary ("auto", "concise" or "detailed"; the alias generate_summary must match it); summaries appear as reasoning output items only when the provider returns them. DeepSeek models combined with function tools accept only effort none or no effort. # Live model catalog Built from the enabled catalog: 56 generation models, 21 text models. Field lines read: name (English meaning): JSON type; rules. UI: catalog label and hint. Quoted UI text comes from the catalog and may be in Russian; always send the machine names and values. Prices change; always call POST /v1/generations/estimate before a paid generation. ## Generation models: 3d ### Tripo 3D - id: model-tripo-h31; category: 3d; base price from 39 credits (basePriceCents 3900; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-tripo-h31; JSON contract: https://lumv.app/v1/generation-models/model-tripo-h31 - UI description: "Создайте готовую 3D-модель по одному изображению" Fields: - generation_mode (Generation mode): enum (string); required; default "h31_image"; one of "p1_image" ("P1 · из изображения"), "p1_text" ("P1 · из текста"), "h31_image" ("H3.1 · из изображения"), "h31_text" ("H3.1 · из текста"); routing only. UI: "Режим Tripo" - prompt (Prompt): string (textarea); required in its scenarios; max length 1024; only in scenario-0, scenario-2. UI: "Описание объекта" / "Опишите форму, материалы и важные детали будущей модели." - image_url (Input image): file via inputAssets; required in its scenarios; accept image/*; new images via upload profile reference_image; only in scenario-1, scenario-3. UI: "Фото объекта" / "Покажите объект целиком, лучше на спокойном фоне." - negative_prompt (Negative prompt (what to avoid)): string (textarea); max length 1024; only in scenario-2. UI: "Что исключить" / "Необязательно: перечислите нежелательные детали." - pbr (PBR materials): boolean; default true; only in scenario-2, scenario-3. UI: "Реалистичные материалы" - texture_alignment (Texture alignment): enum (string); default "original_image"; one of "original_image" ("По изображению"), "geometry" ("По геометрии"); only in scenario-3. UI: "Наложение текстуры" / "Обычно лучше оставить «По изображению»." - texture (Generate texture): boolean; default true. UI: "Добавить текстуру" - auto_size: boolean; default false; only in scenario-2, scenario-3. UI: "Размер в метрах" - face_limit (Polygon (face) limit): number; default 200000; range 48..2000000. UI: "Количество полигонов" - texture_quality (Texture quality): enum (string); default "standard"; one of "standard", "detailed"; only in scenario-2, scenario-3. UI: "Детализация текстуры" - quad (Quad mesh): boolean; default false; only in scenario-2, scenario-3. UI: "Сетка из четырёхугольников" - geometry_quality (Geometry quality): enum (string); required in its scenarios; default "standard"; one of "standard", "detailed"; only in scenario-2, scenario-3. UI: "Детализация формы" - orientation (Model orientation): enum (string); default "default"; one of "default" ("Автоматически"), "align_image" ("По изображению"); only in scenario-3. UI: "Поворот модели" - image_seed (Image seed): number; only in scenario-2. UI: "Seed изображения" - texture_seed (Texture seed): number; only in scenario-2, scenario-3. UI: "Seed текстуры" - model_seed (Geometry seed): number. UI: "Seed формы" Scenarios (checked in order, first match wins): - scenario-0 (when generation_mode = "p1_text"): generation_mode, prompt, texture, face_limit, model_seed; limits: face_limit 48..20000 - scenario-1 (when generation_mode = "p1_image"): generation_mode, image_url, texture, face_limit, model_seed; limits: face_limit 48..20000 - scenario-2 (when generation_mode = "h31_text"): generation_mode, prompt, negative_prompt, pbr, texture, auto_size, face_limit, texture_quality, quad, geometry_quality, image_seed, texture_seed, model_seed; limits: face_limit 1000..2000000 - scenario-3 (fallback): generation_mode, image_url, pbr, texture_alignment, texture, auto_size, face_limit, texture_quality, quad, geometry_quality, orientation, texture_seed, model_seed; limits: face_limit 1000..2000000 Example: {"model":"model-tripo-h31","values":{"generation_mode":"h31_image","pbr":true,"texture_alignment":"original_image","texture":true,"auto_size":false,"face_limit":200000,"texture_quality":"standard","quad":false,"geometry_quality":"standard","orientation":"default"},"inputAssets":[{"fieldName":"image_url","assetId":"REPLACE_WITH_READY_ASSET_ID","position":0}]} ### Hunyuan 3D v3.1 - id: model-hunyuan-3d-v3-1; category: 3d; base price from 66.94 credits (basePriceCents 6694; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-hunyuan-3d-v3-1; JSON contract: https://lumv.app/v1/generation-models/model-hunyuan-3d-v3-1 - UI description: "Детальная 3D-модель с PBR-материалами по тексту или изображению" Fields: - prompt (Prompt): string (textarea); required in its scenarios; max length 600; only in scenario-1. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - input_image_url (Input image): file via inputAssets; required in its scenarios; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображение объекта" / "Вместо текста можно загрузить изображение объекта." - enable_pbr (PBR materials): boolean; default true. UI: "PBR-материалы" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to input_image_url): input_image_url, enable_pbr - scenario-1 (fallback): prompt, enable_pbr Example: {"model":"model-hunyuan-3d-v3-1","values":{"prompt":"Describe the desired result","enable_pbr":true},"inputAssets":[]} ### Meshy 6 3D - id: model-meshy-6-3d; category: 3d; base price from 38.25 credits (basePriceCents 3825; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-meshy-6-3d; JSON contract: https://lumv.app/v1/generation-models/model-meshy-6-3d - UI description: "Создание текстурированной 3D-модели по тексту или нескольким ракурсам" Fields: - prompt (Prompt): string (textarea); required in its scenarios; max length 600; only in scenario-1. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; required in its scenarios; max 4 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения объекта" / "Вместо текста можно загрузить от 1 до 4 ракурсов объекта." - mode (Mode): enum (string); default "full"; one of "preview" ("Быстрый черновик"), "full" ("Готовая модель"). UI: "Этап генерации" - should_texture (Generate textures): boolean; default true. UI: "Добавить текстуры" - enable_pbr (PBR materials): boolean; default false. UI: "PBR-материалы" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): image_urls, mode, should_texture, enable_pbr - scenario-1 (fallback): prompt, mode, should_texture, enable_pbr Example: {"model":"model-meshy-6-3d","values":{"prompt":"Describe the desired result","mode":"full","should_texture":true,"enable_pbr":false},"inputAssets":[]} ## Generation models: image ### GPT Image 2 - id: model-gpt-image-2; category: image; base price from 7 credits (basePriceCents 700; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-gpt-image-2; JSON contract: https://lumv.app/v1/generation-models/model-gpt-image-2 - UI description: "Создание и точное редактирование изображений" Fields: - prompt (Prompt): string (textarea); required; max length 32000. UI: "Что хотите создать?" / "Опишите изображение или желаемые изменения." - image_urls (Input or reference images): file list via inputAssets; max 16 files; accept image/*; new images via upload profile reference_image. UI: "Референсы (необязательно)" / "Добавьте до 16 изображений, чтобы изменить их или сохранить стиль и композицию." - image_size (Image size): string (dimensions WxH or option); default "1024x768"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "3392x2400" ("3392 × 2400 (297:210) · A4 альбом"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "2400x3392" ("2400 × 3392 (210:297) · A4 портрет"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"), "816x1024" ("4:5 · 1K"), "1640x2048" ("4:5 · 2K"), "3280x4096" ("4:5 · 4K"), "1024x816" ("5:4 · 1K"), "2048x1640" ("5:4 · 2K"), "4096x3280" ("5:4 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "1K"; one of "1K", "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." - quality (Quality): enum (string); default "medium"; one of "low" ("Быстрое"), "medium" ("Среднее"), "high" ("Высокое"). UI: "Качество" - num_images (Number of images): number; default 1; range 1..4. UI: "Количество вариантов" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg", "webp". UI: "Формат файла" - mask_url (Edit mask): file via inputAssets; accept image/*; new images via upload profile image_mask; requires image_urls. UI: "Маска редактирования" / "Необязательно. Укажите область изменений; работает вместе с референсом." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution, quality, num_images, output_format, mask_url - scenario-1 (fallback): prompt, image_urls, image_size, image_resolution, quality, num_images, output_format, mask_url Example: {"model":"model-gpt-image-2","values":{"prompt":"Describe the desired result","image_size":"1024x768","quality":"medium","num_images":1,"output_format":"png"},"inputAssets":[]} ### Nano Banana 2 - id: model-nano-banana-2; category: image; base price from 10 credits (basePriceCents 1000; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-nano-banana-2; JSON contract: https://lumv.app/v1/generation-models/model-nano-banana-2 - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 50000. UI: "Что хотите создать?" / "Опишите сцену или изменения естественным языком." - image_urls (Input or reference images): file list via inputAssets; max 14 files; accept image/*; new images via upload profile reference_image. UI: "Референсы (необязательно)" / "Добавьте до 14 изображений, чтобы изменить их или сохранить стиль и композицию." - image_size (Image size): string (dimensions WxH or option); default "auto"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "512x512" ("1:1 · 0.5K"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "512x384" ("4:3 · 0.5K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "384x512" ("3:4 · 0.5K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "512x288" ("16:9 · 0.5K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "288x512" ("9:16 · 0.5K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "344x512" ("2:3 · 0.5K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "512x344" ("3:2 · 0.5K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "512x216" ("21:9 · 0.5K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"), "408x512" ("4:5 · 0.5K"), "816x1024" ("4:5 · 1K"), "1640x2048" ("4:5 · 2K"), "3280x4096" ("4:5 · 4K"), "512x408" ("5:4 · 0.5K"), "1024x816" ("5:4 · 1K"), "2048x1640" ("5:4 · 2K"), "4096x3280" ("5:4 · 4K"), "512x128" ("4:1 · 0.5K"), "1024x256" ("4:1 · 1K"), "2048x512" ("4:1 · 2K"), "4096x1024" ("4:1 · 4K"), "128x512" ("1:4 · 0.5K"), "256x1024" ("1:4 · 1K"), "512x2048" ("1:4 · 2K"), "1024x4096" ("1:4 · 4K"), "512x64" ("8:1 · 0.5K"), "1024x128" ("8:1 · 1K"), "2048x256" ("8:1 · 2K"), "4096x512" ("8:1 · 4K"), "64x512" ("1:8 · 0.5K"), "128x1024" ("1:8 · 1K"), "256x2048" ("1:8 · 2K"), "512x4096" ("1:8 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "1K"; one of "0.5K", "1K", "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." - num_images (Number of images): number; default 1; range 1..4. UI: "Количество вариантов" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg", "webp". UI: "Формат файла" - seed (Random seed): number. UI: "Seed" / "Для повторяемого результата." - enable_web_search (Use web search): boolean; default false. UI: "Использовать веб-поиск" / "Помогает модели учитывать актуальную информацию." - thinking_level (Reasoning depth): enum (string); one of "minimal" ("Минимальная"), "high" ("Высокая"). UI: "Глубина рассуждения" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution, num_images, output_format, seed, enable_web_search, thinking_level - scenario-1 (fallback): prompt, image_urls, image_size, image_resolution, num_images, output_format, seed, enable_web_search, thinking_level Example: {"model":"model-nano-banana-2","values":{"prompt":"Describe the desired result","image_size":"auto","image_resolution":"1K","num_images":1,"output_format":"png","enable_web_search":false},"inputAssets":[]} ### GPT Image 2.5 Flare - id: model-gpt-image-2-5-flare; category: image; base price from 1.79 credits (basePriceCents 179; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-gpt-image-2-5-flare; JSON contract: https://lumv.app/v1/generation-models/model-gpt-image-2-5-flare - UI description: "Быстрое создание и редактирование изображений нового поколения" Fields: - prompt (Prompt): string (textarea); required; max length 32000. UI: "Что хотите создать?" / "Опишите изображение или точные изменения естественным языком." - image_urls (Input or reference images): file list via inputAssets; max 16 files; accept image/png,image/jpeg,image/webp; new images via upload profile reference_image. UI: "Референсы (необязательно)" / "Добавьте до 16 изображений — модель автоматически перейдёт в режим редактирования." - image_size (Image size): string (dimensions WxH or option); default "1024x1024"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "3392x2400" ("3392 × 2400 (297:210) · A4 альбом"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "2400x3392" ("2400 × 3392 (210:297) · A4 портрет"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"), "816x1024" ("4:5 · 1K"), "1640x2048" ("4:5 · 2K"), "3280x4096" ("4:5 · 4K"), "1024x816" ("5:4 · 1K"), "2048x1640" ("5:4 · 2K"), "4096x3280" ("5:4 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "1K"; one of "1K", "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." - quality (Quality): enum (string); default "medium"; one of "low" ("Быстрое"), "medium" ("Среднее"), "high" ("Высокое"), "xhigh" ("Очень высокое"), "max" ("Максимальное"). UI: "Качество" - num_images (Number of images): number; default 1; range 1..4. UI: "Количество вариантов" - background (Background): enum (string); default "auto"; one of "auto" ("Авто"), "opaque" ("Непрозрачный"), "transparent" ("Прозрачный"). UI: "Фон" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg", "webp". UI: "Формат файла" - input_fidelity (Reference fidelity): enum (string); default "high"; one of "low" ("Обычная"), "high" ("Высокая"). UI: "Точность референса" - mask_url (Edit mask): file via inputAssets; accept image/png; new images via upload profile image_mask; requires image_urls. UI: "Маска редактирования" / "Прозрачная область маски будет изменена." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution, quality, num_images, background, output_format, input_fidelity, mask_url - scenario-1 (fallback): prompt, image_urls, image_size, image_resolution, quality, num_images, background, output_format, input_fidelity, mask_url Example: {"model":"model-gpt-image-2-5-flare","values":{"prompt":"Describe the desired result","image_size":"1024x1024","quality":"medium","num_images":1,"background":"auto","output_format":"png","input_fidelity":"high"},"inputAssets":[]} ### GPT Image 2.5 Sunburst - id: model-gpt-image-2-5-sunburst; category: image; base price from 1.79 credits (basePriceCents 179; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-gpt-image-2-5-sunburst; JSON contract: https://lumv.app/v1/generation-models/model-gpt-image-2-5-sunburst - UI description: "Максимум деталей и точности для создания и редактирования" Fields: - prompt (Prompt): string (textarea); required; max length 32000. UI: "Что хотите создать?" / "Опишите изображение или точные изменения естественным языком." - image_urls (Input or reference images): file list via inputAssets; max 16 files; accept image/png,image/jpeg,image/webp; new images via upload profile reference_image. UI: "Референсы (необязательно)" / "Добавьте до 16 изображений — модель автоматически перейдёт в режим редактирования." - image_size (Image size): string (dimensions WxH or option); default "1024x1024"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "3392x2400" ("3392 × 2400 (297:210) · A4 альбом"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "2400x3392" ("2400 × 3392 (210:297) · A4 портрет"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"), "816x1024" ("4:5 · 1K"), "1640x2048" ("4:5 · 2K"), "3280x4096" ("4:5 · 4K"), "1024x816" ("5:4 · 1K"), "2048x1640" ("5:4 · 2K"), "4096x3280" ("5:4 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "1K"; one of "1K", "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." - quality (Quality): enum (string); default "medium"; one of "low" ("Быстрое"), "medium" ("Среднее"), "high" ("Высокое"), "xhigh" ("Очень высокое"), "max" ("Максимальное"). UI: "Качество" - num_images (Number of images): number; default 1; range 1..4. UI: "Количество вариантов" - background (Background): enum (string); default "auto"; one of "auto" ("Авто"), "opaque" ("Непрозрачный"), "transparent" ("Прозрачный"). UI: "Фон" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg", "webp". UI: "Формат файла" - input_fidelity (Reference fidelity): enum (string); default "high"; one of "low" ("Обычная"), "high" ("Высокая"). UI: "Точность референса" - mask_url (Edit mask): file via inputAssets; accept image/png; new images via upload profile image_mask; requires image_urls. UI: "Маска редактирования" / "Прозрачная область маски будет изменена." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution, quality, num_images, background, output_format, input_fidelity, mask_url - scenario-1 (fallback): prompt, image_urls, image_size, image_resolution, quality, num_images, background, output_format, input_fidelity, mask_url Example: {"model":"model-gpt-image-2-5-sunburst","values":{"prompt":"Describe the desired result","image_size":"1024x1024","quality":"medium","num_images":1,"background":"auto","output_format":"png","input_fidelity":"high"},"inputAssets":[]} ### Nano Banana 2 Lite - id: model-nano-banana-2-lite; category: image; base price from 2.98 credits (basePriceCents 298; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-nano-banana-2-lite; JSON contract: https://lumv.app/v1/generation-models/model-nano-banana-2-lite - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 4 files; accept image/*; new images via upload profile reference_image. UI: "Изображения для редактирования" / "Необязательно: добавьте референсы для быстрого редактирования." - image_size (Image size): string (dimensions WxH or option); default "auto"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1024x576" ("16:9 · 1K"), "576x1024" ("9:16 · 1K"), "680x1024" ("2:3 · 1K"), "1024x680" ("3:2 · 1K"), "1024x440" ("21:9 · 1K"), "816x1024" ("4:5 · 1K"), "1024x816" ("5:4 · 1K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size - scenario-1 (fallback): prompt, image_urls, image_size Example: {"model":"model-nano-banana-2-lite","values":{"prompt":"Describe the desired result","image_size":"auto"},"inputAssets":[]} ### Nano Banana Pro - id: model-nano-banana-pro; category: image; base price from 17.85 credits (basePriceCents 1785; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-nano-banana-pro; JSON contract: https://lumv.app/v1/generation-models/model-nano-banana-pro - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 14 files; accept image/*; new images via upload profile reference_image. UI: "Изображения для редактирования" / "Необязательно: до 14 изображений-референсов." - image_size (Image size): string (dimensions WxH or option); default "auto"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"), "816x1024" ("4:5 · 1K"), "1640x2048" ("4:5 · 2K"), "3280x4096" ("4:5 · 4K"), "1024x816" ("5:4 · 1K"), "2048x1640" ("5:4 · 2K"), "4096x3280" ("5:4 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "1K"; one of "1K", "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." - enable_web_search (Use web search): boolean; default false. UI: "Использовать веб-поиск" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg". UI: "Формат файла" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution, enable_web_search, output_format - scenario-1 (fallback): prompt, image_urls, image_size, image_resolution, enable_web_search, output_format Example: {"model":"model-nano-banana-pro","values":{"prompt":"Describe the desired result","image_size":"auto","image_resolution":"1K","enable_web_search":false,"output_format":"png"},"inputAssets":[]} ### Grok Imagine Image - id: model-grok-imagine-image; category: image; base price from 5.06 credits (basePriceCents 506; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-grok-imagine-image; JSON contract: https://lumv.app/v1/generation-models/model-grok-imagine-image - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 8000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 1 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте исходные изображения, чтобы внести изменения." - image_size (Image size): string (dimensions WxH or option); default "1024x1024"; one of "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1024x576" ("16:9 · 1K"), "576x1024" ("9:16 · 1K"), "680x1024" ("2:3 · 1K"), "1024x680" ("3:2 · 1K"), "1024x512" ("2:1 · 1K"), "1024x464" ("20:9 · 1K"), "1024x472" ("19.5:9 · 1K"), "472x1024" ("9:19.5 · 1K"), "464x1024" ("9:20 · 1K"), "512x1024" ("1:2 · 1K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size - scenario-1 (fallback): prompt, image_size Example: {"model":"model-grok-imagine-image","values":{"prompt":"Describe the desired result","image_size":"1024x1024"},"inputAssets":[]} ### Grok Imagine Image 2.0 - id: model-grok-imagine-image-2; category: image; base price from 11.8 credits (basePriceCents 1180; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-grok-imagine-image-2; JSON contract: https://lumv.app/v1/generation-models/model-grok-imagine-image-2 - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 8000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 3 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте исходные изображения, чтобы внести изменения." - image_size (Image size): string (dimensions WxH or option); default "1024x1024"; one of "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2048x2048" ("1:1 · 2K"), "2048x1536" ("4:3 · 2K"), "1536x2048" ("3:4 · 2K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "1024x512" ("2:1 · 1K"), "2048x1024" ("2:1 · 2K"), "1024x464" ("20:9 · 1K"), "2048x920" ("20:9 · 2K"), "1024x472" ("19.5:9 · 1K"), "2048x944" ("19.5:9 · 2K"), "472x1024" ("9:19.5 · 1K"), "944x2048" ("9:19.5 · 2K"), "464x1024" ("9:20 · 1K"), "920x2048" ("9:20 · 2K"), "512x1024" ("1:2 · 1K"), "1024x2048" ("1:2 · 2K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - quality (Quality): enum (string); default "medium"; one of "low" ("Быстро"), "medium" ("Оптимально"). UI: "Качество" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, quality - scenario-1 (fallback): prompt, image_size, quality Example: {"model":"model-grok-imagine-image-2","values":{"prompt":"Describe the desired result","image_size":"1024x1024","quality":"medium"},"inputAssets":[]} ### Grok Imagine Image Quality - id: model-grok-imagine-image-quality; category: image; base price from 8.43 credits (basePriceCents 843; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-grok-imagine-image-quality; JSON contract: https://lumv.app/v1/generation-models/model-grok-imagine-image-quality - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 8000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 3 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте исходные изображения, чтобы внести изменения." - image_size (Image size): string (dimensions WxH or option); default "1024x1024"; one of "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2048x2048" ("1:1 · 2K"), "2048x1536" ("4:3 · 2K"), "1536x2048" ("3:4 · 2K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "1024x512" ("2:1 · 1K"), "2048x1024" ("2:1 · 2K"), "1024x464" ("20:9 · 1K"), "2048x920" ("20:9 · 2K"), "1024x472" ("19.5:9 · 1K"), "2048x944" ("19.5:9 · 2K"), "472x1024" ("9:19.5 · 1K"), "944x2048" ("9:19.5 · 2K"), "464x1024" ("9:20 · 1K"), "920x2048" ("9:20 · 2K"), "512x1024" ("1:2 · 1K"), "1024x2048" ("1:2 · 2K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size - scenario-1 (fallback): prompt, image_size Example: {"model":"model-grok-imagine-image-quality","values":{"prompt":"Describe the desired result","image_size":"1024x1024"},"inputAssets":[]} ### Seedream 4 - id: model-seedream-4; category: image; base price from 5.06 credits (basePriceCents 506; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedream-4; JSON contract: https://lumv.app/v1/generation-models/model-seedream-4 - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте референсы, чтобы перейти в режим редактирования." - image_size (Image size): string (dimensions WxH or option); default "2560x1440"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "2K"; one of "1K", "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution - scenario-1 (fallback): prompt, image_size, image_resolution Example: {"model":"model-seedream-4","values":{"prompt":"Describe the desired result","image_size":"2560x1440"},"inputAssets":[]} ### Seedream 4.5 - id: model-seedream-4-5; category: image; base price from 6.75 credits (basePriceCents 675; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedream-4-5; JSON contract: https://lumv.app/v1/generation-models/model-seedream-4-5 - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте референсы, чтобы перейти в режим редактирования." - image_size (Image size): string (dimensions WxH or option); default "2560x1440"; one of "auto", "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "3840x2160" ("3840 × 2160 (16:9) · 4K"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2160x3840" ("2160 × 3840 (9:16) · 4K"), "2048x2048" ("1:1 · 2K"), "4096x4096" ("1:1 · 4K"), "2048x1536" ("4:3 · 2K"), "4096x3072" ("4:3 · 4K"), "1536x2048" ("3:4 · 2K"), "3072x4096" ("3:4 · 4K"), "2048x1152" ("16:9 · 2K"), "4096x2304" ("16:9 · 4K"), "1152x2048" ("9:16 · 2K"), "2304x4096" ("9:16 · 4K"), "1368x2048" ("2:3 · 2K"), "2728x4096" ("2:3 · 4K"), "2048x1368" ("3:2 · 2K"), "4096x2728" ("3:2 · 4K"), "2048x880" ("21:9 · 2K"), "4096x1752" ("21:9 · 4K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "2K"; one of "2K", "4K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution - scenario-1 (fallback): prompt, image_size, image_resolution Example: {"model":"model-seedream-4-5","values":{"prompt":"Describe the desired result","image_size":"2560x1440"},"inputAssets":[]} ### Seedream 5 Lite - id: model-seedream-5-lite; category: image; base price from 7.59 credits (basePriceCents 759; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedream-5-lite; JSON contract: https://lumv.app/v1/generation-models/model-seedream-5-lite - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте референсы, чтобы перейти в режим редактирования." - image_size (Image size): string (dimensions WxH or option); default "2560x1440"; one of "auto", "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2048x2048" ("1:1 · 2K"), "2048x1536" ("4:3 · 2K"), "1536x2048" ("3:4 · 2K"), "2048x1152" ("16:9 · 2K"), "1152x2048" ("9:16 · 2K"), "1368x2048" ("2:3 · 2K"), "2048x1368" ("3:2 · 2K"), "2048x880" ("21:9 · 2K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "2K"; one of "2K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution - scenario-1 (fallback): prompt, image_size, image_resolution Example: {"model":"model-seedream-5-lite","values":{"prompt":"Describe the desired result","image_size":"2560x1440"},"inputAssets":[]} ### Seedream 5 Pro - id: model-seedream-5-pro; category: image; base price from 22.76 credits (basePriceCents 2276; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedream-5-pro; JSON contract: https://lumv.app/v1/generation-models/model-seedream-5-pro - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Изображения для редактирования" / "Необязательно: добавьте референсы, чтобы перейти в режим редактирования." - image_size (Image size): string (dimensions WxH or option); default "2560x1440"; one of "auto", "1024x1024" ("1024 × 1024 (1:1) · квадрат"), "1024x768" ("1024 × 768 (4:3) · альбом"), "1536x1024" ("1536 × 1024 (3:2) · альбом"), "1920x1080" ("1920 × 1080 (16:9) · Full HD"), "2560x1440" ("2560 × 1440 (16:9) · 2K"), "768x1024" ("768 × 1024 (3:4) · портрет"), "1024x1536" ("1024 × 1536 (2:3) · портрет"), "1080x1920" ("1080 × 1920 (9:16) · Full HD"), "1440x2560" ("1440 × 2560 (9:16) · 2K"), "2048x2048" ("1:1 · 2K"), "2048x1536" ("4:3 · 2K"), "1536x2048" ("3:4 · 2K"), "1024x576" ("16:9 · 1K"), "2048x1152" ("16:9 · 2K"), "576x1024" ("9:16 · 1K"), "1152x2048" ("9:16 · 2K"), "680x1024" ("2:3 · 1K"), "1368x2048" ("2:3 · 2K"), "1024x680" ("3:2 · 1K"), "2048x1368" ("3:2 · 2K"), "1024x440" ("21:9 · 1K"), "2048x880" ("21:9 · 2K"). UI: "Размер изображения" / "Выберите размер и соотношение сторон готового изображения." - image_resolution (Resolution used when the size is automatic): enum (string); default "2K"; one of "1K", "2K"; only when image_size = "auto". UI: "Разрешение при AUTO" / "Определяет детализацию, когда точные размеры выбирает модель." Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, image_size, image_resolution - scenario-1 (fallback): prompt, image_size, image_resolution Example: {"model":"model-seedream-5-pro","values":{"prompt":"Describe the desired result","image_size":"2560x1440"},"inputAssets":[]} ### Qwen Image 2.1 - id: model-qwen-image-2.1; category: image; base price from 5.06 credits (basePriceCents 506; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-qwen-image-2.1; JSON contract: https://lumv.app/v1/generation-models/model-qwen-image-2.1 - UI description: "Изображения, точный текст и редактирование по референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/jpeg,image/png,image/webp; new images via upload profile reference_image; only in scenario-0. UI: "Референсы" - size (Image size or aspect ratio): enum (string); default "1:1"; one of "1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9", "9:21". UI: "Формат изображения" - resolution (Resolution): enum (string); default "1K"; one of "1K", "2K". UI: "Разрешение" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg", "webp". UI: "Формат файла" - prompt_extend (Automatic prompt expansion): boolean; default true. UI: "Улучшать описание" - seed (Random seed): number; range 0..2147483647; step 1. UI: "Seed" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, size, resolution, output_format, prompt_extend, seed - scenario-1 (fallback): prompt, size, resolution, output_format, prompt_extend, seed Example: {"model":"model-qwen-image-2.1","values":{"prompt":"Describe the desired result","size":"1:1","resolution":"1K","output_format":"png","prompt_extend":true},"inputAssets":[]} ### Qwen Image 3 - id: model-qwen-image-3; category: image; base price from 4.05 credits (basePriceCents 405; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-qwen-image-3; JSON contract: https://lumv.app/v1/generation-models/model-qwen-image-3 - UI description: "Изображения, точный текст и редактирование по референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 3 files; accept image/jpeg,image/png,image/webp; new images via upload profile reference_image; only in scenario-0. UI: "Референсы" - size (Image size or aspect ratio): enum (string); default "1:1"; one of "1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9". UI: "Формат изображения" - resolution (Resolution): enum (string); default "1K"; one of "1K", "2K". UI: "Разрешение" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg". UI: "Формат файла" - prompt_extend (Automatic prompt expansion): boolean; default true. UI: "Улучшать описание" - negative_prompt (Negative prompt (what to avoid)): string (textarea); max length 5000. UI: "Что исключить" - seed (Random seed): number; range 0..2147483647; step 1. UI: "Seed" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, size, resolution, output_format, prompt_extend, negative_prompt, seed - scenario-1 (fallback): prompt, size, resolution, output_format, prompt_extend, negative_prompt, seed Example: {"model":"model-qwen-image-3","values":{"prompt":"Describe the desired result","size":"1:1","resolution":"1K","output_format":"png","prompt_extend":true},"inputAssets":[]} ### Qwen Image 3 Pro - id: model-qwen-image-3-pro; category: image; base price from 5.4 credits (basePriceCents 540; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-qwen-image-3-pro; JSON contract: https://lumv.app/v1/generation-models/model-qwen-image-3-pro - UI description: "Изображения, точный текст и редактирование по референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 3 files; accept image/jpeg,image/png,image/webp; new images via upload profile reference_image; only in scenario-0. UI: "Референсы" - size (Image size or aspect ratio): enum (string); default "1:1"; one of "1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9". UI: "Формат изображения" - resolution (Resolution): enum (string); default "1K"; one of "1K", "2K". UI: "Разрешение" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg". UI: "Формат файла" - prompt_extend (Automatic prompt expansion): boolean; default true. UI: "Улучшать описание" - negative_prompt (Negative prompt (what to avoid)): string (textarea); max length 5000. UI: "Что исключить" - seed (Random seed): number; range 0..2147483647; step 1. UI: "Seed" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, size, resolution, output_format, prompt_extend, negative_prompt, seed - scenario-1 (fallback): prompt, size, resolution, output_format, prompt_extend, negative_prompt, seed Example: {"model":"model-qwen-image-3-pro","values":{"prompt":"Describe the desired result","size":"1:1","resolution":"1K","output_format":"png","prompt_extend":true},"inputAssets":[]} ### Nano Banana 2.1 - id: model-nano-banana-2-1; category: image; base price from 3.38 credits (basePriceCents 338; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-nano-banana-2-1; JSON contract: https://lumv.app/v1/generation-models/model-nano-banana-2-1 - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/jpeg,image/png,image/webp; new images via upload profile reference_image; only in scenario-0. UI: "Референсы" - size (Image size or aspect ratio): enum (string); default "1:1"; one of "auto", "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9", "4:5", "5:4", "4:1", "1:4", "8:1", "1:8". UI: "Формат изображения" - resolution (Resolution): enum (string); default "1K"; one of "1K", "2K", "4K". UI: "Разрешение" - output_format (Output file format): enum (string); default "jpeg"; one of "png", "jpeg". UI: "Формат файла" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, size, resolution, output_format - scenario-1 (fallback): prompt, size, resolution, output_format Example: {"model":"model-nano-banana-2-1","values":{"prompt":"Describe the desired result","size":"1:1","resolution":"1K","output_format":"jpeg"},"inputAssets":[]} ### Seedream 5.0 Flash - id: model-seedream-5-flash; category: image; base price from 3.38 credits (basePriceCents 338; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedream-5-flash; JSON contract: https://lumv.app/v1/generation-models/model-seedream-5-flash - UI description: "Создание и редактирование изображений по описанию и референсам" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 10 files; accept image/jpeg,image/png,image/webp; new images via upload profile reference_image; only in scenario-0. UI: "Референсы" - size (Image size or aspect ratio): enum (string); default "1:1"; one of "1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9". UI: "Формат изображения" - resolution (Resolution): enum (string); default "1K"; one of "1K", "1.5K", "2K". UI: "Разрешение" - output_format (Output file format): enum (string); default "png"; one of "png", "jpeg". UI: "Формат файла" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to image_urls): prompt, image_urls, size, resolution, output_format - scenario-1 (fallback): prompt, size, resolution, output_format Example: {"model":"model-seedream-5-flash","values":{"prompt":"Describe the desired result","size":"1:1","resolution":"1K","output_format":"png"},"inputAssets":[]} ## Generation models: music ### ElevenLabs Music v1 - id: model-elevenlabs-music; category: music; base price from 102 credits (basePriceCents 10200; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-music; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-music - UI description: "Создайте законченную музыкальную композицию по описанию" Fields: - prompt (Prompt): string (textarea); required; max length 5000. UI: "Как должна звучать музыка?" / "Опишите жанр, настроение, инструменты, темп и развитие композиции." - music_length_ms (Music length (milliseconds)): enum (JSON number); default 60000; one of 30000 ("30 секунд"), 60000 ("1 минута"), 120000 ("2 минуты"), 180000 ("3 минуты"), 300000 ("5 минут"), 600000 ("10 минут"). UI: "Длительность" - force_instrumental (Instrumental only (no vocals)): boolean; default false. UI: "Без вокала" - output_format (Output file format): enum (string); default "mp3_44100_128"; one of "mp3_44100_128" ("MP3 · 128 kbps"), "mp3_44100_192" ("MP3 · 192 kbps"), "pcm_44100" ("PCM · без сжатия"). UI: "Формат аудио" Example: {"model":"model-elevenlabs-music","values":{"prompt":"Describe the desired result","music_length_ms":60000,"force_instrumental":false,"output_format":"mp3_44100_128"},"inputAssets":[]} ### MiniMax Music 2.6 - id: model-minimax-music-2-6; category: music; base price from 16.86 credits (basePriceCents 1686; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-minimax-music-2-6; JSON contract: https://lumv.app/v1/generation-models/model-minimax-music-2-6 - UI description: "Песни с вокалом, своими словами или инструментальная музыка" Fields: - prompt (Prompt): string (textarea); required; max length 2000. UI: "Как должна звучать музыка?" / "От 10 до 2000 символов." - lyrics (Song lyrics): string (textarea); max length 3500. UI: "Текст песни" / "Необязательно: при пустом тексте слова создаются автоматически." - is_instrumental (Instrumental only (no vocals)): boolean; default false. UI: "Без вокала" Example: {"model":"model-minimax-music-2-6","values":{"prompt":"Describe the desired result","is_instrumental":false},"inputAssets":[]} ### MiniMax Music 3 - id: model-minimax-music-3; category: music; base price from 20.23 credits (basePriceCents 2023; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-minimax-music-3; JSON contract: https://lumv.app/v1/generation-models/model-minimax-music-3 - UI description: "Создайте аудио по описанию" Fields: - prompt (Prompt): string (textarea); required; max length 2000. UI: "Стиль, настроение и инструменты" - lyrics (Song lyrics): string (textarea); required; max length 3500. UI: "Текст песни" / "Метки [verse], [chorus], [outro] размещайте на отдельных строках. Для музыки без вокала используйте [instrumental]." - duration (Duration (seconds)): number; required; default 60; range 1..300; step 1. UI: "Максимальная длительность, секунд" Example: {"model":"model-minimax-music-3","values":{"prompt":"Describe the desired result","lyrics":"Describe the desired result","duration":60},"inputAssets":[]} ### ElevenLabs Music v2 - id: model-elevenlabs-music-v2; category: music; base price from 1011.39 credits (basePriceCents 101139; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-music-v2; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-music-v2 - UI description: "Музыка с вокалом или инструментальная композиция по описанию" Fields: - prompt (Prompt): string (textarea); required; max length 4100. UI: "Как должна звучать музыка?" / "Опишите жанр, настроение, инструменты, темп и развитие композиции." - music_length_ms (Music length (milliseconds)): number; range 3000..600000; step 1000. UI: "Длительность" / "Автоматическая длительность рассчитывается по максимальным 10 минутам. Для точной цены задайте время." - force_instrumental (Instrumental only (no vocals)): boolean; default false. UI: "Без вокала" - output_format (Output file format): enum (string); default "mp3_48000_192"; one of "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "mp3_48000_128", "mp3_48000_192", "mp3_48000_240", "mp3_48000_320", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "ulaw_8000", "alaw_8000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192". UI: "Формат аудио" Example: {"model":"model-elevenlabs-music-v2","values":{"prompt":"Describe the desired result","force_instrumental":false,"output_format":"mp3_48000_192"},"inputAssets":[]} ### ElevenLabs Music v2.5 - id: model-elevenlabs-music-v2-5; category: music; base price from 1011.39 credits (basePriceCents 101139; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-music-v2-5; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-music-v2-5 - UI description: "Музыка с вокалом или инструментальная композиция по описанию" Fields: - prompt (Prompt): string (textarea); required; max length 4100. UI: "Как должна звучать музыка?" / "Опишите жанр, настроение, инструменты, темп и развитие композиции." - music_length_ms (Music length (milliseconds)): number; range 3000..600000; step 1000. UI: "Длительность" / "Автоматическая длительность рассчитывается по максимальным 10 минутам. Для точной цены задайте время." - force_instrumental (Instrumental only (no vocals)): boolean; default false. UI: "Без вокала" - output_format (Output file format): enum (string); default "mp3_48000_192"; one of "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "mp3_48000_128", "mp3_48000_192", "mp3_48000_240", "mp3_48000_320", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "ulaw_8000", "alaw_8000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192". UI: "Формат аудио" Example: {"model":"model-elevenlabs-music-v2-5","values":{"prompt":"Describe the desired result","force_instrumental":false,"output_format":"mp3_48000_192"},"inputAssets":[]} ## Generation models: audio ### ElevenLabs v3 - id: model-elevenlabs-tts-v3; category: audio; base price from 17 credits (basePriceCents 1700; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-tts-v3; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-tts-v3 - UI description: "Естественная озвучка текста с управлением голосом и эмоциями" Fields: - text (Text input (speech text or sound description)): string (textarea); required; max length 10000. UI: "Текст для озвучивания" / "Введите текст и при необходимости добавьте эмоциональные подсказки." - voice (Voice): enum (string); default "Rachel"; one of "Rachel", "Aria", "Roger", "Sarah", "Laura", "Charlie", "George", "Callum", "River", "Liam". UI: "Голос" - stability (Voice stability): number; default 0.5; range 0..1; step 0.1. UI: "Стабильность" / "Ниже — эмоциональнее, выше — ровнее." - language_code (Language code): enum (string); default "ru"; one of "ru" ("Русский"), "en", "de", "fr", "es". UI: "Язык" - timestamps (Return timestamps): boolean; default false. UI: "Добавить таймкоды" - apply_text_normalization (Text normalization): enum (string); default "auto"; one of "auto" ("Автоматически"), "on" ("Всегда"), "off" ("Выключена"). UI: "Нормализация текста" / "Помогает корректно произносить числа и сокращения." Example: {"model":"model-elevenlabs-tts-v3","values":{"text":"Describe the desired result","voice":"Rachel","stability":0.5,"language_code":"ru","timestamps":false,"apply_text_normalization":"auto"},"inputAssets":[]} ### ElevenLabs Sound Effects v2 - id: model-elevenlabs-sound-effects-v2; category: audio; base price from 1.69 credits (basePriceCents 169; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-sound-effects-v2; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-sound-effects-v2 - UI description: "Создайте аудио по описанию" Fields: - text (Text input (speech text or sound description)): string (textarea); required; max length 450. UI: "Какой звук создать?" - duration_seconds (Duration (seconds)): number; required; default 5; range 0.5..22; step 0.5. UI: "Длительность, секунд" - loop (Seamless loop): boolean; default false. UI: "Бесшовное повторение" - prompt_influence (Prompt influence): number; default 0.3; range 0..1; step 0.1. UI: "Точность следования описанию" Example: {"model":"model-elevenlabs-sound-effects-v2","values":{"text":"Describe the desired result","duration_seconds":5,"loop":false,"prompt_influence":0.3},"inputAssets":[]} ### ElevenLabs v4 - id: model-elevenlabs-tts-v4; category: audio; base price from 0.02 credits (basePriceCents 2; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-tts-v4; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-tts-v4 - UI description: "Озвучка текста с эмоциями и управлением голосом" Fields: - text (Text input (speech text or sound description)): string (textarea); required; max length 5000. UI: "Текст для озвучивания" / "Введите текст и при необходимости добавьте эмоциональные подсказки." - voice (Voice): enum (string); default "Rachel"; one of "Rachel", "Aria", "Roger", "Sarah", "Laura", "Charlie", "George", "Callum", "River", "Liam". UI: "Голос" - stability (Voice stability): number; default 0.5; range 0..1; step 0.1. UI: "Стабильность" / "Ниже — эмоциональнее, выше — ровнее." - language_code (Language code): enum (string); default "ru"; one of "ru" ("Русский"), "en", "de", "fr", "es". UI: "Язык" - timestamps (Return timestamps): boolean; default false. UI: "Добавить таймкоды" - apply_text_normalization (Text normalization): enum (string); default "auto"; one of "auto" ("Автоматически"), "on" ("Всегда"), "off" ("Выключена"). UI: "Нормализация текста" / "Помогает корректно произносить числа и сокращения." - similarity_boost (Voice similarity): number; default 0.75; range 0..1; step 0.05. UI: "Сходство с голосом" - output_format (Output file format): enum (string); default "mp3_44100_128"; one of "mp3_44100_128", "mp3_44100_192", "opus_48000_128". UI: "Формат аудио" Example: {"model":"model-elevenlabs-tts-v4","values":{"text":"Describe the desired result","voice":"Rachel","stability":0.5,"language_code":"ru","timestamps":false,"apply_text_normalization":"auto","similarity_boost":0.75,"output_format":"mp3_44100_128"},"inputAssets":[]} ### ElevenLabs v4 Turbo - id: model-elevenlabs-tts-v4-turbo; category: audio; base price from 0.01 credits (basePriceCents 1; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-elevenlabs-tts-v4-turbo; JSON contract: https://lumv.app/v1/generation-models/model-elevenlabs-tts-v4-turbo - UI description: "Озвучка текста с эмоциями и управлением голосом" Fields: - text (Text input (speech text or sound description)): string (textarea); required; max length 5000. UI: "Текст для озвучивания" / "Введите текст и при необходимости добавьте эмоциональные подсказки." - voice (Voice): enum (string); default "Rachel"; one of "Rachel", "Aria", "Roger", "Sarah", "Laura", "Charlie", "George", "Callum", "River", "Liam". UI: "Голос" - stability (Voice stability): number; default 0.5; range 0..1; step 0.1. UI: "Стабильность" / "Ниже — эмоциональнее, выше — ровнее." - language_code (Language code): enum (string); default "ru"; one of "ru" ("Русский"), "en", "de", "fr", "es". UI: "Язык" - timestamps (Return timestamps): boolean; default false. UI: "Добавить таймкоды" - apply_text_normalization (Text normalization): enum (string); default "auto"; one of "auto" ("Автоматически"), "on" ("Всегда"), "off" ("Выключена"). UI: "Нормализация текста" / "Помогает корректно произносить числа и сокращения." - similarity_boost (Voice similarity): number; default 0.75; range 0..1; step 0.05. UI: "Сходство с голосом" - output_format (Output file format): enum (string); default "mp3_44100_128"; one of "mp3_44100_128", "mp3_44100_192", "opus_48000_128". UI: "Формат аудио" Example: {"model":"model-elevenlabs-tts-v4-turbo","values":{"text":"Describe the desired result","voice":"Rachel","stability":0.5,"language_code":"ru","timestamps":false,"apply_text_normalization":"auto","similarity_boost":0.75,"output_format":"mp3_44100_128"},"inputAssets":[]} ### Gemini 3.1 Flash TTS - id: model-gemini-3-1-flash-tts; category: audio; base price from 0.03 credits (basePriceCents 3; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-gemini-3-1-flash-tts; JSON contract: https://lumv.app/v1/generation-models/model-gemini-3-1-flash-tts - UI description: "Многоязычная озвучка с выразительной интонацией" Fields: - text (Text input (speech text or sound description)): string (textarea); required; max length 50000. UI: "Текст для озвучивания" - voice (Voice): enum (string); default "Kore"; one of "Kore", "Puck", "Charon", "Zephyr", "Aoede", "Leda", "Orus", "Fenrir". UI: "Голос" - style_instructions (Speaking style instructions): string (textarea); max length 5000. UI: "Манера речи" / "Опишите интонацию, темп и настроение." - language_code (Language code): enum (string); default "Russian (Russia)"; one of "Russian (Russia)", "English (US)", "French (France)", "German (Germany)", "Spanish (Spain)". UI: "Язык" - output_format (Output file format): enum (string); default "mp3"; one of "mp3", "wav", "ogg_opus". UI: "Формат аудио" Example: {"model":"model-gemini-3-1-flash-tts","values":{"text":"Describe the desired result","voice":"Kore","language_code":"Russian (Russia)","output_format":"mp3"},"inputAssets":[]} ### xAI TTS 1 - id: model-xai-tts-1; category: audio; base price from 0.01 credits (basePriceCents 1; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-xai-tts-1; JSON contract: https://lumv.app/v1/generation-models/model-xai-tts-1 - UI description: "Многоязычная озвучка с выразительной интонацией" Fields: - text (Text input (speech text or sound description)): string (textarea); required; max length 15000. UI: "Текст для озвучивания" - voice (Voice): enum (string); default "eve"; one of "eve", "ara", "rex", "sal", "leo". UI: "Голос" - language_code (Language code): enum (string); default "ru"; one of "ru", "auto", "en", "fr", "de", "es-ES". UI: "Язык" Example: {"model":"model-xai-tts-1","values":{"text":"Describe the desired result","voice":"eve","language_code":"ru"},"inputAssets":[]} ## Generation models: video ### Kling Video 3 Pro - id: model-kling-video-v3-pro; category: video; base price from 115 credits (basePriceCents 11500; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-kling-video-v3-pro; JSON contract: https://lumv.app/v1/generation-models/model-kling-video-v3-pro - UI description: "Создайте видео со звуком по текстовому описанию" Fields: - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Исходное изображение" / "Необязательно: добавьте стартовый кадр, чтобы включить режим изображения в видео." - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что должно произойти?" / "Опишите движение, сцену, камеру и желаемое настроение." - duration (Duration (seconds)): enum (string); required; default "5"; one of "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15". UI: "Длительность, секунд" / "От 3 до 15 секунд. Длительность влияет на стоимость." - generate_audio (Generate an audio track): boolean; default true. UI: "Создать звук" / "Добавляет подходящие звуки и атмосферу; влияет на стоимость." - negative_prompt (Negative prompt (what to avoid)): string (textarea); max length 2500. UI: "Чего избегать" / "Необязательно: артефакты, нежелательные объекты или движения." - cfg_scale (Prompt adherence (CFG scale)): number; default 0.5; range 0..1; step 0.1. UI: "Точность следования запросу" / "Обычно достаточно значения 0.5." - shot_type (Camera shot type): enum (string); default "intelligent"; one of "intelligent" ("Автоматически"), "customize" ("По описанию"). UI: "Работа камеры" - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: изображение, к которому должно прийти видео." - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): start_image_url, prompt, duration, generate_audio, negative_prompt, cfg_scale, shot_type, end_image_url - scenario-1 (fallback): prompt, duration, generate_audio, negative_prompt, cfg_scale, shot_type, aspect_ratio Example: {"model":"model-kling-video-v3-pro","values":{"prompt":"Describe the desired result","duration":"5","generate_audio":true,"cfg_scale":0.5,"shot_type":"intelligent","aspect_ratio":"16:9"},"inputAssets":[]} ### Gemini Omni 1.1 Flash - id: model-gemini-omni-1-1-flash; category: video; base price from 47.82 credits (basePriceCents 4782; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-gemini-omni-1-1-flash; JSON contract: https://lumv.app/v1/generation-models/model-gemini-omni-1-1-flash - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 2 files; accept image/*; new images via upload profile reference_image. UI: "Референсные кадры" / "Необязательно: загрузите изображение, чтобы оживить его." - duration (Duration (seconds)): enum (JSON number); default 8; one of 4, 6, 8, 10. UI: "Длительность" - resolution (Resolution): enum (string); default "360p"; one of "360p", "720p", "1080p", "4K". UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16". UI: "Формат кадра" Example: {"model":"model-gemini-omni-1-1-flash","values":{"prompt":"Describe the desired result","duration":8,"resolution":"360p","aspect_ratio":"16:9"},"inputAssets":[]} ### Gemini Omni Flash - id: model-gemini-omni-flash; category: video; base price from 95.63 credits (basePriceCents 9563; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-gemini-omni-flash; JSON contract: https://lumv.app/v1/generation-models/model-gemini-omni-flash - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - image_urls (Input or reference images): file list via inputAssets; max 3 files; accept image/*; new images via upload profile reference_image. UI: "Референсные кадры" / "Необязательно: загрузите изображение, чтобы оживить его." - duration (Duration (seconds)): enum (JSON number); default 6; one of 4, 6, 8, 10. UI: "Длительность" - resolution (Resolution): enum (string); default "720p"; one of "720p", "1080p", "4K". UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1", "4:3", "3:4". UI: "Формат кадра" Example: {"model":"model-gemini-omni-flash","values":{"prompt":"Describe the desired result","duration":6,"resolution":"720p","aspect_ratio":"16:9"},"inputAssets":[]} ### Kling 3 Standard - id: model-kling-video-v3-standard; category: video; base price from 86.1 credits (basePriceCents 8610; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-kling-video-v3-standard; JSON contract: https://lumv.app/v1/generation-models/model-kling-video-v3-standard - UI description: "Создание видео по описанию или исходному изображению" Fields: - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Исходное изображение" / "Необязательно: добавьте стартовый кадр." - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - duration (Duration (seconds)): enum (JSON number); required; default 5; one of 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15. UI: "Длительность, секунд" - generate_audio (Generate an audio track): boolean; default true. UI: "Создать звук" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): start_image_url, prompt, duration, generate_audio - scenario-1 (fallback): prompt, duration, generate_audio, aspect_ratio Example: {"model":"model-kling-video-v3-standard","values":{"prompt":"Describe the desired result","duration":5,"generate_audio":true,"aspect_ratio":"16:9"},"inputAssets":[]} ### Kling 3 Turbo Pro - id: model-kling-video-v3-turbo-pro; category: video; base price from 70.15 credits (basePriceCents 7015; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-kling-video-v3-turbo-pro; JSON contract: https://lumv.app/v1/generation-models/model-kling-video-v3-turbo-pro - UI description: "Создание видео по описанию или исходному изображению" Fields: - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Исходное изображение" / "Необязательно: добавьте стартовый кадр." - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - duration (Duration (seconds)): enum (JSON number); required; default 5; one of 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15. UI: "Длительность, секунд" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): start_image_url, prompt, duration - scenario-1 (fallback): prompt, duration, aspect_ratio Example: {"model":"model-kling-video-v3-turbo-pro","values":{"prompt":"Describe the desired result","duration":5,"aspect_ratio":"16:9"},"inputAssets":[]} ### Kling 3 Turbo Standard - id: model-kling-video-v3-turbo-standard; category: video; base price from 54.2 credits (basePriceCents 5420; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-kling-video-v3-turbo-standard; JSON contract: https://lumv.app/v1/generation-models/model-kling-video-v3-turbo-standard - UI description: "Создание видео по описанию или исходному изображению" Fields: - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Исходное изображение" / "Необязательно: добавьте стартовый кадр." - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - duration (Duration (seconds)): enum (JSON number); required; default 5; one of 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15. UI: "Длительность, секунд" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): start_image_url, prompt, duration - scenario-1 (fallback): prompt, duration, aspect_ratio Example: {"model":"model-kling-video-v3-turbo-standard","values":{"prompt":"Describe the desired result","duration":5,"aspect_ratio":"16:9"},"inputAssets":[]} ### MiniMax H3 - id: model-minimax-h3; category: video; base price from 66.95 credits (basePriceCents 6695; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-minimax-h3; JSON contract: https://lumv.app/v1/generation-models/model-minimax-h3 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы оживить его." - duration (Duration (seconds)): enum (JSON number); default 5; one of 5, 6, 8, 10, 12, 15. UI: "Длительность" - resolution (Resolution): enum (string); default "2K"; one of "2K". UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1". UI: "Формат кадра" - prompt_expansion_mode (Prompt expansion mode): enum (string); default "balanced"; one of "balanced" ("Сбалансированное"), "quality" ("Максимальное качество"). UI: "Улучшение запроса" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution, aspect_ratio, prompt_expansion_mode - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, prompt_expansion_mode Example: {"model":"model-minimax-h3","values":{"prompt":"Describe the desired result","duration":5,"resolution":"2K","aspect_ratio":"16:9","prompt_expansion_mode":"balanced"},"inputAssets":[]} ### MiniMax H3 Max - id: model-minimax-h3-max; category: video; base price from 31.9 credits (basePriceCents 3190; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-minimax-h3-max; JSON contract: https://lumv.app/v1/generation-models/model-minimax-h3-max - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы оживить его." - duration (Duration (seconds)): enum (JSON number); default 5; one of 5, 6, 8, 10, 12, 15. UI: "Длительность" - resolution (Resolution): enum (string); default "480P"; one of "480P", "768P", "1080P". UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1". UI: "Формат кадра" - prompt_expansion_mode (Prompt expansion mode): enum (string); default "balanced"; one of "balanced" ("Сбалансированное"), "quality" ("Максимальное качество"). UI: "Улучшение запроса" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution, aspect_ratio, prompt_expansion_mode - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, prompt_expansion_mode Example: {"model":"model-minimax-h3-max","values":{"prompt":"Describe the desired result","duration":5,"resolution":"480P","aspect_ratio":"16:9","prompt_expansion_mode":"balanced"},"inputAssets":[]} ### MiniMax Hailuo 2.3 - id: model-minimax-hailuo-2-3; category: video; base price from 22.32 credits (basePriceCents 2232; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-minimax-hailuo-2-3; JSON contract: https://lumv.app/v1/generation-models/model-minimax-hailuo-2-3 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 2500. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы оживить его." - duration (Duration (seconds)): enum (JSON number); default 6; one of 6, 10. UI: "Длительность" - resolution (Resolution): enum (string); default "768p"; one of "768p". UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1". UI: "Формат кадра" - prompt_optimizer (Automatic prompt optimization): boolean; default true. UI: "Улучшить запрос автоматически" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution, aspect_ratio, prompt_optimizer - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, prompt_optimizer Example: {"model":"model-minimax-hailuo-2-3","values":{"prompt":"Describe the desired result","duration":6,"resolution":"768p","aspect_ratio":"16:9","prompt_optimizer":true},"inputAssets":[]} ### Grok Imagine Video - id: model-grok-imagine-video; category: video; base price from 151.74 credits (basePriceCents 15174; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-grok-imagine-video; JSON contract: https://lumv.app/v1/generation-models/model-grok-imagine-video - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - duration (Duration (seconds)): enum (JSON number); default 6; one of 6, 10. UI: "Длительность" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "1:1", "2:3", "3:2", "16:9", "9:16"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration - scenario-1 (fallback): prompt, duration, aspect_ratio Example: {"model":"model-grok-imagine-video","values":{"prompt":"Describe the desired result","duration":6,"aspect_ratio":"16:9"},"inputAssets":[]} ### Grok Imagine Video 1.5 - id: model-grok-imagine-video-1-5; category: video; base price from 141.6 credits (basePriceCents 14160; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-grok-imagine-video-1-5; JSON contract: https://lumv.app/v1/generation-models/model-grok-imagine-video-1-5 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - duration (Duration (seconds)): number; default 6; range 1..15; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio Example: {"model":"model-grok-imagine-video-1-5","values":{"prompt":"Describe the desired result","duration":6,"resolution":"720p","aspect_ratio":"16:9"},"inputAssets":[]} ### Seedance 1.5 Pro - id: model-seedance-1-5-pro; category: video; base price from 121.4 credits (basePriceCents 12140; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedance-1-5-pro; JSON contract: https://lumv.app/v1/generation-models/model-seedance-1-5-pro - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): enum (JSON number); default 4; one of 4, 8, 12. UI: "Длительность" - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-seedance-1-5-pro","values":{"prompt":"Describe the desired result","duration":4,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### Seedance 1.0 Pro - id: model-seedance-1-pro; category: video; base price from 101.15 credits (basePriceCents 10115; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedance-1-pro; JSON contract: https://lumv.app/v1/generation-models/model-seedance-1-pro - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - duration (Duration (seconds)): enum (JSON number); default 5; one of 5, 10. UI: "Длительность" - resolution (Resolution): enum (string); default "720p"; one of "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution - scenario-1 (fallback): prompt, duration, resolution Example: {"model":"model-seedance-1-pro","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p"},"inputAssets":[]} ### Seedance 2 - id: model-seedance-2; category: video; base price from 255.4 credits (basePriceCents 25540; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedance-2; JSON contract: https://lumv.app/v1/generation-models/model-seedance-2 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 4..15; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "auto" ("Автоматически"), "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-seedance-2","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### Seedance 2.5 - id: model-seedance-2-5; category: video; base price from 398.7 credits (basePriceCents 39870; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedance-2-5; JSON contract: https://lumv.app/v1/generation-models/model-seedance-2-5 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 4..30; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "auto" ("Автоматически"), "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-seedance-2-5","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### Seedance 2 Fast - id: model-seedance-2-fast; category: video; base price from 204 credits (basePriceCents 20400; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedance-2-fast; JSON contract: https://lumv.app/v1/generation-models/model-seedance-2-fast - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 4..15; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "auto" ("Автоматически"), "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-seedance-2-fast","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### Seedance 2 Mini - id: model-seedance-2-mini; category: video; base price from 101.15 credits (basePriceCents 10115; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-seedance-2-mini; JSON contract: https://lumv.app/v1/generation-models/model-seedance-2-mini - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 4..15; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "auto" ("Автоматически"), "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-seedance-2-mini","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### Wan 2.2 Fast - id: model-wan-2-2-fast; category: video; base price from 67.43 credits (basePriceCents 6743; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-wan-2-2-fast; JSON contract: https://lumv.app/v1/generation-models/model-wan-2-2-fast - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, resolution - scenario-1 (fallback): prompt, resolution, aspect_ratio Example: {"model":"model-wan-2-2-fast","values":{"prompt":"Describe the desired result","resolution":"720p","aspect_ratio":"16:9"},"inputAssets":[]} ### Wan 2.5 - id: model-wan-2-5; category: video; base price from 101.15 credits (basePriceCents 10115; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-wan-2-5; JSON contract: https://lumv.app/v1/generation-models/model-wan-2-5 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - duration (Duration (seconds)): enum (JSON number); default 5; one of 5, 10. UI: "Длительность" - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "832*480"; one of "832*480" ("832 × 480"), "480*832" ("480 × 832"), "1280*720" ("1280 × 720"), "720*1280" ("720 × 1280"), "1920*1080" ("1920 × 1080"), "1080*1920" ("1080 × 1920"); only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution - scenario-1 (fallback): prompt, duration, aspect_ratio Example: {"model":"model-wan-2-5","values":{"prompt":"Describe the desired result","duration":5,"aspect_ratio":"832*480"},"inputAssets":[]} ### Wan 2.6 - id: model-wan-2-6; category: video; base price from 126.45 credits (basePriceCents 12645; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-wan-2-6; JSON contract: https://lumv.app/v1/generation-models/model-wan-2-6 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - duration (Duration (seconds)): enum (JSON number); default 5; one of 5, 10, 15. UI: "Длительность" - resolution (Resolution): enum (string); default "720p"; one of "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, duration, resolution - scenario-1 (fallback): prompt, duration, resolution Example: {"model":"model-wan-2-6","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p"},"inputAssets":[]} ### Wan 2.7 - id: model-wan-2-7; category: video; base price from 151.75 credits (basePriceCents 15175; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-wan-2-7; JSON contract: https://lumv.app/v1/generation-models/model-wan-2-7 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): enum (JSON number); default 5; one of 5, 10, 15. UI: "Длительность" - resolution (Resolution): enum (string); default "720p"; one of "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "16:9", "9:16", "1:1", "4:3", "3:4"; only in scenario-0, scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio Example: {"model":"model-wan-2-7","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9"},"inputAssets":[]} ### Wan 3.0 - id: model-wan-3; category: video; base price from 118 credits (basePriceCents 11800; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-wan-3; JSON contract: https://lumv.app/v1/generation-models/model-wan-3 - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 2..30; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "adaptive" ("По исходному кадру"), "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-wan-3","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### Wan 3.0 Prime - id: model-wan-3-prime; category: video; base price from 118 credits (basePriceCents 11800; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-wan-3-prime; JSON contract: https://lumv.app/v1/generation-models/model-wan-3-prime - UI description: "Создание видео по описанию или исходному изображению" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 2..30; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "720p"; one of "480p", "720p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "adaptive" ("По исходному кадру"), "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-0, scenario-1. UI: "Формат кадра" - generate_audio (Generate an audio track): boolean; default true. UI: "Сгенерировать звук" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution, aspect_ratio, generate_audio - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio, generate_audio Example: {"model":"model-wan-3-prime","values":{"prompt":"Describe the desired result","duration":5,"resolution":"720p","aspect_ratio":"16:9","generate_audio":true},"inputAssets":[]} ### MiniMax H3 Max Turbo - id: model-minimax-h3-max-turbo; category: video; base price from 21.1 credits (basePriceCents 2110; exact price: estimate) - docs: https://lumv.app/docs/api/models/model-minimax-h3-max-turbo; JSON contract: https://lumv.app/v1/generation-models/model-minimax-h3-max-turbo - UI description: "Быстрое видео со звуком по описанию или первому и последнему кадрам" Fields: - prompt (Prompt): string (textarea); required; max length 20000. UI: "Что нужно создать?" / "Опишите сюжет, композицию, стиль и важные детали." - start_image_url (Start image (first frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; only in scenario-0. UI: "Стартовый кадр" / "Необязательно: загрузите изображение, чтобы анимировать его." - end_image_url (End image (last frame)): file via inputAssets; accept image/*; new images via upload profile reference_image; requires start_image_url; only in scenario-0. UI: "Финальный кадр" / "Необязательно: задайте кадр, которым завершится видео." - duration (Duration (seconds)): number; default 5; range 5..15; step 1. UI: "Длительность, сек." - resolution (Resolution): enum (string); default "480p"; one of "480p", "768p", "1080p"; only in scenario-0, scenario-1. UI: "Качество видео" - aspect_ratio (Aspect ratio): enum (string); default "16:9"; one of "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"; only in scenario-1. UI: "Формат кадра" Scenarios (checked in order, first match wins): - scenario-0 (when a file is attached to start_image_url): prompt, start_image_url, end_image_url, duration, resolution - scenario-1 (fallback): prompt, duration, resolution, aspect_ratio Example: {"model":"model-minimax-h3-max-turbo","values":{"prompt":"Describe the desired result","duration":5,"resolution":"480p","aspect_ratio":"16:9"},"inputAssets":[]} ## Text models (OpenAI-compatible) ### Claude Fable 5.1 - model: claude-fable-5-1 (catalog id model-chat-claude-fable-5-1); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-claude-fable-5-1 - context 1000000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 10, output 50, cached input 0.25 (charged in credits) - UI description: "Длинные сложные задачи и исследования" Example: {"model":"claude-fable-5-1","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Claude Haiku 4.5 - model: claude-haiku-4-5-20251001 (catalog id model-chat-claude-haiku-4-5-20251001); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-claude-haiku-4-5-20251001 - context 200000 tokens; max output 64000 tokens - reasoning_effort: low, medium, high - indicative price, USD per 1M tokens: input 1.2, output 6 (charged in credits) - UI description: "Быстрый и экономичный Claude" Example: {"model":"claude-haiku-4-5-20251001","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Claude Opus 5 - model: claude-opus-5 (catalog id model-chat-claude-opus-5); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-claude-opus-5 - context 1000000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 3, output 15 (charged in credits) - UI description: "Флагман Anthropic для агентных задач" Example: {"model":"claude-opus-5","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Claude Sonnet 5 - model: claude-sonnet-5 (catalog id model-chat-claude-sonnet-5); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-claude-sonnet-5 - context 1000000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh - indicative price, USD per 1M tokens: input 1.275, output 6.375 (charged in credits) - UI description: "Код, документы и профессиональная работа" Example: {"model":"claude-sonnet-5","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### DeepSeek V4.1 Flash - model: deepseek-v4-1-flash (catalog id model-chat-deepseek-v4-flash); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-deepseek-v4-flash - context 1000000 tokens; max output 384000 tokens - reasoning_effort: none, low, high, max - indicative price, USD per 1M tokens: input 0.6, output 2.4, cached input 0.012 (charged in credits) - UI description: "Быстрый DeepSeek с визуальным анализом" Example: {"model":"deepseek-v4-1-flash","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### DeepSeek V4 Pro - model: deepseek-v4-pro (catalog id model-chat-deepseek-v4-pro); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-deepseek-v4-pro - context 1000000 tokens; max output 384000 tokens - reasoning_effort: none, low, high, max - indicative price, USD per 1M tokens: input 0.513, output 2.565 (charged in credits) - UI description: "Сильное рассуждение и программирование" Example: {"model":"deepseek-v4-pro","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Gemini 3.8 Flash - model: gemini-3.8-flash (catalog id model-chat-gemini-3.7-flash); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gemini-3.7-flash - context 1048576 tokens; max output 65536 tokens - reasoning_effort: low, medium, high - indicative price, USD per 1M tokens: input 0.9, output 4.5, cached input 0.09 (charged in credits) - UI description: "Быстрая мультимодальная модель Google" Example: {"model":"gemini-3.8-flash","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-6 Luna - model: gpt-6-luna (catalog id model-chat-gpt-5-6-luna); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-5-6-luna - context 1050000 tokens; max output 128000 tokens - reasoning_effort: none, low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 0.16, output 0.8, cached input 0.016 (charged in credits) - UI description: "Быстрые повседневные задачи" Example: {"model":"gpt-6-luna","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-6 Sol - model: gpt-6-sol (catalog id model-chat-gpt-5-6-sol); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-5-6-sol - context 1050000 tokens; max output 128000 tokens - reasoning_effort: none, low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 3.2, output 16, cached input 0.32 (charged in credits) - UI description: "Сложное программирование, анализ и агенты" Example: {"model":"gpt-6-sol","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-6 Astra - model: gpt-6-astra (catalog id model-chat-gpt-6-astra); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-6-astra - context 1050000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 10, output 50, cached input 1 (charged in credits) - UI description: "Самая мощная модель OpenAI" Example: {"model":"gpt-6-astra","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Grok 4.6 - model: grok-4.6 (catalog id model-chat-grok-4.6); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-grok-4.6 - context 500000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh - indicative price, USD per 1M tokens: input 2.4, output 7.2 (charged in credits) - UI description: "Долгие агентные и инженерные задачи" Example: {"model":"grok-4.6","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Kimi K3 - model: kimi-k3 (catalog id model-chat-kimi-k3); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-kimi-k3 - context 1000000 tokens; max output 131072 tokens - reasoning_effort: not supported - indicative price, USD per 1M tokens: input 3.42, output 17.1 (charged in credits) - UI description: "Мультимодальная модель с контекстом 1M" Example: {"model":"kimi-k3","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Claude Opus 5.5 - model: claude-opus-5-5 (catalog id model-chat-claude-opus-5-5); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-claude-opus-5-5 - context 1000000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 4, output 20, cached input 0.2 (charged in credits) - UI description: "Сложные агентные задачи и визуальный анализ" Example: {"model":"claude-opus-5-5","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Grok 4.7 - model: grok-4-7 (catalog id model-chat-grok-4-7); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-grok-4-7 - context 256000 tokens; max output 128000 tokens - reasoning_effort: high, xhigh - indicative price, USD per 1M tokens: input 2.4, output 7.2, cached input 0.6 (charged in credits) - UI description: "Долгие агентные и инженерные задачи" Example: {"model":"grok-4-7","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Claude Sonnet 5.5 - model: claude-sonnet-5-5 (catalog id model-chat-claude-sonnet-5-5); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-claude-sonnet-5-5 - context 1000000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 2.5, output 12.5 (charged in credits) - UI description: "Новый Claude для кода и агентных задач" Example: {"model":"claude-sonnet-5-5","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-5.5 - model: gpt-5.5 (catalog id model-chat-gpt-5.5); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-5.5 - context 1050000 tokens; max output 128000 tokens - reasoning_effort: none, low, medium, high, xhigh - indicative price, USD per 1M tokens: input 6, output 36 (charged in credits) - UI description: "Сложное программирование и профессиональные задачи" Example: {"model":"gpt-5.5","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-5.6 Luna - model: gpt-5.6-luna (catalog id model-chat-gpt-5.6-luna); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-5.6-luna - context 1050000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh - indicative price, USD per 1M tokens: input 0.112, output 0.672, cached input 0.012 (charged in credits) - UI description: "Быстрые и экономичные ответы" Example: {"model":"gpt-5.6-luna","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-5.6 Sol - model: gpt-5.6-sol (catalog id model-chat-gpt-5.6-sol); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-5.6-sol - context 1050000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh - indicative price, USD per 1M tokens: input 2.8, output 16.8, cached input 0.28 (charged in credits) - UI description: "Сложный код и длительные агентные задачи" Example: {"model":"gpt-5.6-sol","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-5.6 Terra - model: gpt-5.6-terra (catalog id model-chat-gpt-5.6-terra); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-5.6-terra - context 1050000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh - indicative price, USD per 1M tokens: input 1.12, output 6.72, cached input 0.112 (charged in credits) - UI description: "Сбалансированный код и анализ" Example: {"model":"gpt-5.6-terra","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### GPT-6.1 Sol - model: gpt-6.1-sol (catalog id model-chat-gpt-6.1-sol); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gpt-6.1-sol - context 1050000 tokens; max output 128000 tokens - reasoning_effort: low, medium, high, xhigh, max - indicative price, USD per 1M tokens: input 3.2, output 16, cached input 0.16 (charged in credits) - UI description: "Новейшая модель OpenAI для кода, документов и агентов" Example: {"model":"gpt-6.1-sol","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024} ### Gemini 4 Argon - model: gemini-4-argon (catalog id model-chat-gemini-4-argon); POST /v1/chat/completions or POST /v1/responses - docs: https://lumv.app/docs/api/models/model-chat-gemini-4-argon - context 1000000 tokens; max output 1000000 tokens - reasoning_effort: not supported - indicative price, USD per 1M tokens: input 3.2, output 16, cached input 0.32 (charged in credits) - UI description: "Сложный код, анализ и мультимодальный контекст до 1M токенов" Example: {"model":"gemini-4-argon","messages":[{"role":"user","content":"Hello!"}],"max_tokens":1024}