Model ids from this catalog go in the model field of every request. Each entry carries the limits the API enforces: max_chars and max_request_chars for text, max_pages, max_bytes, and formats for documents, with the rate as credits_per_1k_chars or credits_per_page.
Response#
The served model catalog.
modelsarray of objectsRequiredShow propertiesHide properties
models[].idstringRequiredModel id to send as the model field.
models[].namestringRequiredDisplay name.
models[].productstringRequiredCapability of the model: "tts", "translation", "ocr", "extraction", or "stt".
models[].max_charsinteger or nullRequiredPer-request ceiling on the text field in characters. Null for models that read files, such as OCR, Document Extraction, and transcription.
models[].max_request_charsinteger or nullRequiredCeiling on the request's total billable characters, where that differs from max_chars. Null when it does not. Translation models bill every field. This ceiling bounds the text together with instructions, context, examples, do_not_translate strings, and glossary.
models[].credits_per_1k_charsinteger or nullRequiredCost in credits per 1000 input characters, billed per character and rounded up to the next hundredth of a credit. TTS requests that set timestamps bill at 1.25x this rate. Null for models billed by page or by recording length.
models[].reference_credits_per_1k_charsinteger or nullRequiredCost in credits per 1000 characters of material the model reads without translating: instructions, context, examples, do_not_translate strings, and glossary. Null for models that have no such material.
models[].credits_per_pagenumber or nullRequiredCost in credits per page for models billed by page, such as OCR and Document Extraction, exact to a hundredth. Null for models billed otherwise.
models[].large_schema_credits_per_pagenumber or nullRequiredCost in credits per page a Document Extraction request takes when its schema declares large_schema_min_leaves leaf fields or more. Null for other models.
models[].large_schema_min_leavesinteger or nullRequiredLeaf count from which a Document Extraction schema bills at large_schema_credits_per_page. Null for other models.
models[].max_leavesinteger or nullRequiredMost leaf fields one Document Extraction schema may declare, counted after arrays and nested objects are unfolded; more answers 400 schema_invalid. Null for other models.
models[].credits_per_hourinteger or nullRequiredCost in credits per hour of audio for models billed by audio length: a recording's exact length, or the audio received over a realtime connection. Null for models billed otherwise.
models[].max_pagesinteger or nullRequiredMost pages one request accepts; null for models not billed by page. Document Extraction's ceiling is lower than OCR's.
models[].max_duration_secondsinteger or nullRequiredLongest recording one request accepts, in seconds; null for models that do not read audio.
models[].diarization_limit_secondsinteger or nullRequiredLength at which speaker attribution stops, in seconds, well below max_duration_seconds. With diarization on, a recording this long or longer answers 400 diarization_audio_too_long; with it off, it transcribes normally. Null for models that do not read audio.
models[].max_session_secondsinteger or nullRequiredMost audio one realtime connection accepts, in seconds; reaching it ends the session as an end frame would. Null for models that do not serve a connection.
models[].encodingsarray of objects or nullRequiredAudio encodings a realtime connection's start frame may declare, each with the sample rates it accepts. Null for models that do not serve a connection.
models[].max_bytesinteger or nullRequiredLargest decoded file one request accepts, in bytes. Null for models that read text.
models[].formatsarray of strings or nullRequiredFile formats the model reads: "pdf", "png", "jpeg", "webp" for OCR and Document Extraction; "mp3", "wav", "flac", "ogg", "m4a", "aac", "webm" for transcription. Null for models that read text.
models[].min_request_creditsnumberRequiredSmallest charge one request to this model can incur, in credits.
models[].voicesarray of stringsRequiredIds of the voices on this model's roster, the values the voice field accepts. GET /v1/voices carries each voice's details. Empty for models without voices.
models[].sourcesarray of strings or nullRequiredSource language codes the translation source field accepts alongside "auto"; null for non-translation models.
models[].targetstring or nullRequiredTarget language code the model translates into; null for non-translation models.
object"list"Requireddataarray of objectsRequiredThe same models in OpenAI's list shape. A client built on an OpenAI SDK lists them with models.list(), and models carries the detail.
Show propertiesHide properties
data[].idstringRequiredModel id, as in models.
data[].object"model"Requireddata[].createdintegerRequiredUnix time of the UTC day the model opened, in seconds.
data[].owned_by"paxalabs"Required