XPlor3
Model reference

Model reference

The modelSlug, input fields, accepted values and rules of every XPlor3 model, for the REST API and MCP.

Every page in this section is generated from the same model registry the API checks requests against. What is written here is what POST /v1/jobs and the MCP generate tool accept: if a value is listed, the API takes it.

Reading a field table

TypeMeaning
stringText.
string (one of)One of the values in the Rules column.
integerA whole number.
booleantrue or false.
string[] (... upload ids)A list of ids from POST /v1/uploads, not URLs.
object[]A list of objects; each object's fields are in their own table on that model's page.
  • A field you leave out takes its Default.
  • Unknown field names are dropped without an error. If a setting seems to have no effect, check its spelling.
  • Rules by setting apply to models with several versions behind them: a tier, a mode, or whether a reference file is attached. A request that breaks one is refused with 400 before any credits move, and the message names the field.
  • The same data is available as JSON: GET /v1/models on the REST API (inputSchema.fields, defaults, variants) and the describe_model tool over MCP.

Every model

Image

ModelmodelSlugMaker
GPT Image 2.5gpt-image-2-5OpenAI
Nano Banananano-bananaGoogle
Nano Banana 2nano-banana-2Google
Nano Banana 2.1nano-banana-2-1Google
Nano Banana Pronano-banana-proGoogle
Seedream 4seedream-4ByteDance
Seedream 4.5seedream-4-5ByteDance
Seedream 5seedream-5ByteDance
GPT Image 1.5gpt-image-1-5OpenAI
GPT Image 2gpt-image-2OpenAI
Grok Imagine Image 2grok-imagine-image-2xAI
Grok Imagine Imagegrok-imagine-imagexAI
Wan 2.7 Imagewan-2-7-imageAlibaba
Qwen 3qwen-3Alibaba
Qwen 2qwen-2Alibaba
Qwen 2.1qwen-2-1Alibaba
Z-Imagez-imageAlibaba
Recraft Remove Backgroundrecraft-remove-backgroundRecraft
Recraft Crisp Upscalerecraft-crisp-upscaleRecraft

Video

ModelmodelSlugMaker
Kling 3kling-3Kuaishou
Wan 3 Videowan-3-videoAlibaba
Seedance 1seedance-1ByteDance
Seedance 1.5 Proseedance-1-5-proByteDance
Seedance 2seedance-2ByteDance
Seedance 2.5seedance-2-5ByteDance
Kling 3 Turbokling-3-turboKuaishou
Kling 3 Motion Controlkling-3-motion-controlKuaishou
Kling 2.6kling-2-6Kuaishou
Grok Imagine Video 1.5grok-imagine-video-1-5xAI
Grok Imagine Videogrok-imagine-videoxAI
Wan 2.7 Videowan-2-7-videoAlibaba
Wan 2.6 Videowan-2-6-videoAlibaba
Happy Horse 1happy-horse-1Alibaba
Happy Horse 1.1happy-horse-1-1Alibaba
MiniMax H3minimax-h3MiniMax
Veo 3.1veo-3-1Google
Vidu Q4vidu-q4ShengShu

Speech

ModelmodelSlugMaker
Gemini 3.8 Flash TTSgemini-ttsGoogle

Limits and errors

The error format, the codes you will meet most, per-minute request limits, and how to handle them.

GPT Image 2.5

OpenAI visual model with two rendering styles, an optional transparent background, and up to 4K output.

On this page

Reading a field tableEvery modelImageVideoSpeech