Torii Image Translator API

Bring Torii's image translation, OCR, inpainting, typesetting and colorization into your own apps, paid for with the same credits as the rest of Torii.

Get an API key Read the docs

Get started in minutes

Start translating images with just a few lines of code.

1
Sign up and get your key

Create a free account, then create an API key at the bottom of this page.
2
Top up your credits

The API spends the same credits as the rest of Torii. Top up your account to start translating.
3
Make your first request

Call the endpoints to translate, run OCR, inpaint, typeset or colorize. Each has example code below.

Limits and rate throttling

Every API key is rate limited, and uploads have size limits, so requests stay fast for everyone.

Standard rate limit

Your API key has a default throttling limit configured to manage steady traffic:

Steady rate 1 request / second Standard processing rate per API key.

Burst capacity 100 requests Spikes are queued and processed sequentially.

Image and file limits

Uploaded images have to fit these limits, which keeps processing fast:

Max file size 50 MB Maximum allowed file payload size.

Max side length 100,000 px Height and width limit per image.

Total resolution 100 MP Maximum total resolution limit.

Handling limit errors

Past the rate limit, requests are rejected with 429 Too Many Requests or 503 Service Unavailable. Past a size limit, they get a validation error. Retry with exponential backoff, so your app handles these gracefully.

API reference

Pick an endpoint to see its parameters, responses and example code.

Typeset endpoint

Render multiple textboxes onto a pre-cleaned image with custom fonts, colors, and alignments.

POST https://api.toriitranslate.com/api/typeset

Credits cost

Each request to the typeset endpoint costs 0.02 credits, scaling up with size to at most 0.1 credits: 0.02 for every 4,000 characters of text or 4 megapixels of image, whichever is larger. A request can have up to 500 text boxes, 5,000 characters per box and 20,000 in total. Boxes must be on or near the image, and together they can cover it at most 4 times, a rotated box counting the area it spans.

Build your request

Text boxes (JSON)

Font

Min font size

Disable stroke

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token.

Parameters

form data

Send these as multipart/form-data fields. Booleans are the strings true and false; anything other than true counts as false.

file file required

The image to draw on. Coordinates are in its stored pixels, and EXIF rotation is ignored. Up to 100,000 px on its longest side and 100 megapixels.

text_boxes string (JSON array) required

The text boxes to draw, as a JSON array of objects.

Limit: 500 boxes and 20,000 characters in total

Each object takes these fields:

text string required

The text to draw.

Limit: 5,000 characters

x · y · width · height number required unless polygon is set

The box's top-left corner and size, in pixels. Width and height must be above 0.

polygon array optional

Four [x, y] corners of a rotated or skewed box, such as [[10,10],[210,20],[205,80],[5,70]]. Replaces x, y, width and height, and must enclose an area.

alignment string optional

How lines line up inside the box.

Default: center
Values: leftcenterright

text_color string optional

The text colour, as a hex code.

Default: #ffffff

stroke_color string optional

The outline colour, as a hex code.

Default: #000000

fontsize integer optional

The font size to start from, in pixels. Torii shrinks the text until it fits the box.

Default: half the image height
Range: 1 to 1000

angle number optional

The rotation, in degrees. Vertical text needs 90 to stand straight.

Default: 0

direction string optional

The writing direction.

Default: un, which picks a direction for you
Values: left_to_right
top_to_bottomvertical; needs Japanese or Chinese text of 2 or more characters

source_lang string optional

The language code of the text, which picks the right letterforms.

Default: detected from the text

font string optional

The font for every box. Pick one that covers your text's language.

Default: noto

All fonts

min_font_size integer optional

The smallest font size, in pixels, that Torii may shrink text to so it fits. A value outside the range falls back to the default.

Default: 6
Range: 6 to 100

stroke_disabled boolean optional

Turns off the outline on every box.

Default: false

Response headers

success boolean

Whether the typeset operation was successful.

credits number

The amount of credits remaining.

Response body

The response content is a JSON object.

{
    "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII+..."
}

Example code

Translate endpoint

Translate images or raw text between dozens of languages. Image translation automatically handles text detection, inpainting and typesetting, with lots of other settings and features available.

POST https://api.toriitranslate.com/api/v2/upload

Credits cost

Each request to the translate endpoint costs at least 1 credit, but it may cost more depending on the chosen translation model, context and input/output character length.

Build your request

Target language

Translator

Font

Text align

Disable stroke

Min font size

Bubbles only

Custom prompt

Additional context

BYOK provider

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token.

Parameters

form data

Send these as multipart/form-data fields, with the image under file. Booleans are the strings true and false; anything other than true counts as false.

file file required

The image to translate, up to 50 MB, 100,000 px on its longest side and 100 megapixels.

target_lang string required

The language to translate into, as a language code.

All language codes

translator string optional

The model that translates. An unknown value falls back to the default.

Default: gemini-3.1-flash-lite

All models

reasoning_effort string optional

How much the model thinks before it translates. More thinking can help with hard pages, but it uses more tokens, so it costs more credits. Some models always think a little, even with none. An unknown value falls back to the default.

Default: none
Values: nonelowmediumhigh

font string optional

The font for the translated text. Pick one that covers your target language. An unknown value falls back to the default.

Default: wildwords

All fonts

text_align string optional

How translated lines line up inside their bubble.

Default: auto, which follows the alignment of each original text
Values: autoleftcenterright

min_font_size integer optional

The smallest font size, in pixels, that Torii may shrink text to so it fits. A value outside the range falls back to the default.

Default: 6
Range: 6 to 100

stroke_disabled boolean optional

Turns off the outline drawn around text. Torii matches each text's outline and colours to the original, which can look wrong on documents.

Default: false

bubbles_only boolean optional

Translates only text inside speech bubbles, plus long text read with high confidence outside them. Sound effects and background text stay as they are.

Default: false

source_langs_whitelist string (JSON array) optional

Translates and erases only text detected in these languages, such as ["ja", "zh"]. Text in any other language stays as it is, and text whose language can't be detected is always kept. Use the same codes as target_lang.

Default: every language

custom_prompt string optional

Extra instructions for the model, such as a tone or how to translate certain names.

Limit: 2,000 characters

context string optional

Background that helps the translation: names, characters, events, earlier dialogue. To chain pages, send None with the first one, then send back the context each response returns. Any other text is used as plain background.

Limit: 10,000 characters; only the last 10,000 are kept

x-byok-<provider> string optional

Your own API key for an AI provider (BYOK). The translation then runs on your account with that provider, and Torii charges a flat 1 credit per image, or 0.1 per text request. Put the provider's name in place of <provider>.

Values: x-byok-openrouterOpenRouter
x-byok-openaiOpenAI
x-byok-googleGoogle Gemini
x-byok-anthropicAnthropic Claude
x-byok-deepseekDeepSeek
x-byok-xaixAI Grok
x-byok-localYour self-hosted model's key, if it needs one; see x-byok-local-url

x-byok-local-url string required for a self-hosted model

The base URL of your self-hosted, OpenAI-compatible endpoint, such as https://my-llm-server.com/v1. Set translator to the model name it serves. Local and private network addresses are refused, so expose it through a tunnel.

x-byok-fallback boolean optional

What happens when your own key fails, for example when the model blocks the content or times out. With true, Torii's own models translate the request instead and charge their usual credits, and metadata.fallback_model names the model that ran. With false, the request fails with your provider's error.

Default: false

Response headers

success boolean

Whether the request was successful. If true, the response contains the translated or cleaned image, else the response contains an error message.

credits number

The amount of credits remaining in the account.

Response body

The response content is a JSON object containing the translated image as a Data URL, the inpainted image as a Data URL, the detected text objects, remaining account balance, and request execution metadata. The context key will be empty if a context chain has not been started (see above for explanation).

{
    "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII...",
    "inpainted": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII...",
    "context": "...",
    "text": [
        {
            "x": 623.0, 
            "y": 326.5, 
            "width": 50.0, 
            "height": 141.0, 
            "text": "Tanjiro", 
            "originalText": "炭治郎", 
            "textAlign": "center", 
            "strokeColor": "#f9f7f9", 
            "lineWidth": 10, 
            "fillColor": "#0e0c0f", 
            "font": "36px WildWords", 
            "addFontBackground": false, 
            "addFontBorder": false, 
            "addBackgroundColor": "#ffffff",
            "rotation": 0.0,
            "angle": 0.0,
            "layout": "h",
            "textDir": "ltr"
        }
    ],
    "metadata": {
        "credits_used": 1.25,
        "ocr_time": 0.452,
        "inpaint_time": 0.381,
        "translation_time": 1.124,
        "render_time": 0.089,
        "total_texts_count": 14,
        "filtered_texts_count": 0,
        "prompt_tokens": 420,
        "completion_tokens": 150,
        "reasoning_tokens": 0,
        "total_tokens": 570,
        "attempts": [
            {
                "model": "google/gemini-3.1-flash-lite",
                "duration": 1.124,
                "status": "success",
                "stage": "translation"
            }
        ]
    }
}

{
    "text": [
        "Translated sentence one.",
        "Translated sentence two.",
        "Translated paragraph three."
    ],
    "detected_lang": "ja",
    "metadata": {
        "credits_used": 0.25,
        "translation_time": 0.854,
        "total_texts_count": 3,
        "filtered_texts_count": 0,
        "prompt_tokens": 120,
        "completion_tokens": 45,
        "reasoning_tokens": 0,
        "total_tokens": 165,
        "attempts": [
            {
                "model": "google/gemini-3.1-flash-lite",
                "duration": 0.854,
                "status": "success",
                "stage": "translation"
            }
        ]
    },
    "context": "..."
}

Response fields

image string

The base64-encoded Data URL of the final translated image. Only present for image translation requests (DataType: IMAGE).

inpainted string

The base64-encoded Data URL of the inpainted image (image with source text removed). Only present for image translation requests (DataType: IMAGE).

original string

Optional. The base64-encoded Data URL of the original source image. Only present for image translation requests (DataType: IMAGE) when a remote image URL is supplied and the user is authenticated.

context string

Optional. The updated translation context string. Only present if a context chain is active or has been updated.

detected_lang string

The detected ISO language code of the input text (e.g. "ja", "ko", "zh"). Only present for text translation requests (DataType: TEXT).

text array

An array of translated contents. Always present. For image responses, this is an array of objects detailing bounding box coordinates and styling rules. For text responses, this is an array of raw translated strings.

text[].x / y number

The X and Y pixel coordinates of the center point of the text bounding box.

text[].width / height number

The dimensions (width and height) of the text box in pixels.

text[].text string

The final translated text content rendered inside the box.

text[].originalText string

The original detected source text.

text[].textAlign string

Text alignment style ("left", "center", "right").

text[].fillColor / strokeColor string

The text fill and outline/stroke colors in hexadecimal format (e.g. #ffffff).

text[].lineWidth number

The width of the text stroke/outline border in pixels.

text[].font string

CSS font property value specifying size and family (e.g. "36px WildWords").

text[].addFontBackground / addFontBorder boolean

Options indicating whether extra background fills or custom border outlines are applied behind/around the font.

text[].addBackgroundColor string

Hexadecimal background color for the text background if enabled.

text[].rotation / angle number

The text block's rotation in radians and degrees, respectively.

text[].layout string

The orientation layout direction of the text block ("h" for horizontal, "v" for vertical).

text[].textDir string

The layout reading direction of the text flow ("ltr" for left-to-right, "rtl" for right-to-left).

metadata object

Execution metrics, stage timings, token consumption, reasoning thoughts, and fallback attempt waterfall.

metadata.credits_used number

The exact amount of credits deducted for the request.

metadata.ocr_time number

Duration of the OCR text detection stage in seconds.

metadata.inpaint_time number

Duration of the text removal/inpainting stage in seconds.

metadata.translation_time number

Total duration of translation attempts in seconds.

metadata.summarization_time number

Optional. Total duration of context summarization attempts in seconds (when context summarization runs).

metadata.render_time number

Duration of text rendering and font typesetting in seconds.

metadata.total_texts_count number

Total number of detected text paragraphs/bubbles.

metadata.filtered_texts_count number

Number of text paragraphs filtered out by the source languages whitelist.

metadata.prompt_tokens number

Input prompt tokens consumed across all successful LLM calls.

metadata.completion_tokens number

Output completion tokens generated across all successful LLM calls.

metadata.reasoning_tokens number

Thinking/reasoning tokens generated by reasoning models.

metadata.total_tokens number

Total tokens consumed across all successful LLM calls.

metadata.reasoning string

Optional. The internal thinking/reasoning process returned by the translation model.

metadata.fallback_model string

Optional. The fallback model that completed the translation if the primary model failed.

metadata.fallback_reason string

Optional. The reason the primary model failed and triggered a fallback (e.g. "content_filter", "timeout", "schema_validation_failed").

metadata.attempts array

An array of objects representing each model attempt and fallback in the execution waterfall.

metadata.attempts[].model string

Model identifier used for this attempt.

metadata.attempts[].duration number

Duration of this attempt in seconds.

metadata.attempts[].status string

Status of the attempt ("success" or "failed").

metadata.attempts[].stage string

Pipeline stage ("translation" or "summarization").

metadata.attempts[].reason string

Optional. The reason the attempt failed if status is "failed".

Example code

OCR endpoint

A powerful OCR endpoint that returns highly detailed information, including text orientation, font sizes, and extracted colors (text, background, stroke) for each paragraph.

POST https://api.toriitranslate.com/api/v2/ocr

Credits cost

Each request to the ocr endpoint costs 1 credit.

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token.

Parameters

form data

Send the image as a multipart/form-data field named file, or send its raw bytes as the request body with Content-Type: application/octet-stream.

file file required

The image to read, from 50 × 50 px up to 100,000 px on its longest side and 100 megapixels.

Response headers

success boolean

Whether the request was successful. If true, the response contains the OCR result, else the response contains an error message.

credits number

The amount of credits remaining in the account.

Response body

The response content is a JSON array of detailed paragraph objects.

[
    {
        "text": "Thank you very much!",
        "polygon": [[10, 320], [170, 320], [170, 370], [10, 370]],
        "fontsize": 24,
        "angle": 0.0,
        "alignment": "center",
        "direction": "left_to_right",
        "bg_color": [255, 255, 255],
        "text_color": [0, 0, 0],
        "stroke_color": [0, 0, 0],
        "has_dominant_bg_color": true,
        "confidence": 0.998,
        "language_details": {
            "language": "ENGLISH",
            "code": "en",
            "confidence": 0.999
        },
        "removed": false,
        "lines": [
            {
                "text": "Thank you",
                "polygon": [[11, 326], [165, 327], [165, 361], [11, 360]],
                "confidence": 0.998,
                "angle": 0.0,
                "direction": "left_to_right",
                "language_details": {
                    "language": "ENGLISH",
                    "code": "en",
                    "confidence": 0.999
                },
                "removed": false,
                "words": [
                    {
                        "text": "Thank",
                        "polygon": [[12, 327], [100, 327], [99, 361], [11, 360]],
                        "confidence": 0.998,
                        "direction": "left_to_right",
                        "symbols": [
                            {
                                "text": "T",
                                "polygon": [[12, 327], [25, 327], [25, 361], [12, 361]],
                                "confidence": 0.999
                            }
                        ]
                    }
                ]
            }
        ]
    }
]

Response fields

paragraph array

The root response is an array of objects, where each object represents a detected paragraph of text.

paragraph[].text string

The full recognized text content of the paragraph.

paragraph[].polygon array

A list of 4 [x, y] points defining the oriented bounding box of the paragraph.

paragraph[].fontsize number

The estimated median font size of the text in pixels.

paragraph[].angle number

The rotation angle of the paragraph in degrees (0-360).

paragraph[].alignment string

The text alignment within the paragraph ("left", "center", "right").

paragraph[].direction string

The text flow direction of the paragraph (e.g., "left_to_right", "top_to_bottom").

paragraph[].bg_color / text_color / stroke_color array

The detected colors in [B, G, R] format.

paragraph[].language_details object

Detailed language detection results.

paragraph[].language_details.language string

The full name of the detected language (e.g., "ENGLISH", "JAPANESE").

paragraph[].language_details.code string

The ISO 639-1 language code (e.g., "en", "ja").

paragraph[].language_details.confidence number

The confidence score of the language detection (0 to 1).

paragraph[].removed boolean

Indicates if the paragraph was filtered out (e.g., detected as noise or furigana).

paragraph[].confidence number

The average confidence score of the recognition (0 to 1).

paragraph[].lines array

An array of detailed line objects within the paragraph.

paragraph[].lines[].direction string

The text flow direction (e.g., "left_to_right", "top_to_bottom").

paragraph[].lines[].language_details object

Detailed language detection for this specific line.

paragraph[].lines[].language_details.language string

Full name of the line-level language.

paragraph[].lines[].language_details.code string

ISO 639-1 code for the line.

paragraph[].lines[].language_details.confidence number

Detection confidence for the line.

paragraph[].lines[].removed boolean

Mainly used for detected furigana (small reading aids for Kanji).

paragraph[].lines[].words array

An array of word objects within the line.

paragraph[].lines[].words[].polygon array

A list of 4 [x, y] points defining the word's bounding box.

paragraph[].lines[].words[].symbols array

An array of individual character/symbol objects.

paragraph[].lines[].words[].symbols[].text string

The recognized character.

paragraph[].lines[].words[].symbols[].polygon array

A list of 4 [x, y] points defining the symbol's bounding box.

paragraph[].lines[].words[].symbols[].confidence number

The recognition confidence for this specific character.

Example code

Inpaint endpoint

Remove text or objects from images. Returns a clean image with the masked areas filled in by Torii's inpainting model.

POST https://api.toriitranslate.com/api/inpaint

Credits cost

Each request to the inpaint endpoint costs 0.02 credits.

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token.

Parameters

form data

Send both images as multipart/form-data fields.

image file required

The image to clean, up to 100,000 px on its longest side and 100 megapixels.

mask file required

A black-and-white image the same size as image. Every pixel that isn't black marks an area to erase and fill in.

Response headers

success boolean

Whether the request was successful.

credits number

The amount of credits remaining.

Response body

The response content is a JSON object.

{
    "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII=..."
}

Example code

Colorize endpoint

Add color to a black-and-white image, using the model you pick. Returns a JPEG the same size as your upload.

POST https://api.toriitranslate.com/api/colorize

Credits cost

Each image costs at least the credits listed under colorize_model, or a flat 1 credit with your own provider key (BYOK). metadata.credits_used reports what each request cost.

Failed and refused requests cost nothing, with one exception: without your own key, images Grok blocks still cost credits, because xAI bills for them.

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token.

Parameters

form data

Send these as multipart/form-data.

image file required

The black-and-white image to color.

Limit: 10,000 px on its longest side, and the long side at most 3 times the short side

colorize_model string optional

The model that colors the image, with its credits per image.

Values: localTorii's own model, 1 credit. It runs on Torii's servers, so no provider's content filter applies.
museMeta Muse Image, 12 credits
gptOpenAI GPT Image 2, 16 credits
grokxAI Grok Imagine, 25 credits
geminiGoogle Nano Banana 2.1, 46 credits
Default: muse

colorize_prompt string optional

Extra instructions for the model, such as a character's hair color. local ignores it.

Limit: 2,100 characters; anything longer is cut off

x-byok-<provider> string optional

Your own API key for the model's provider (BYOK). The image then runs on your account with that provider, and Torii charges a flat 1 credit. local takes no key.

Values: x-byok-openrouterFor muse and gpt
x-byok-xaiFor grok
x-byok-googleFor gemini

Response headers

success boolean

Whether the request was successful. If false, the body is a plain-text message saying why.

credits number

The amount of credits remaining.

Response body

The response content is a JSON object.

{
    "success": true,
    "image": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL...",
    "credits": 988,
    "metadata": {
        "credits_used": 12,
        "colorize_time": 6.412,
        "colorize_model": "muse"
    }
}

image string

The colored image as a base64-encoded JPEG Data URL, the same size as your upload.

credits number

The amount of credits remaining.

metadata.credits_used number

The credits this request cost.

metadata.colorize_time number

How long the model took, in seconds.

metadata.colorize_model string

The model that colored the image.

Errors

A failed request sets success to false, with a reason such as an image past the limits, too few credits for the model, or a model refusing it. local colors one image at a time across all users and answers busy if it can't start within a couple of seconds, so retry those after a short delay.

Example code

Credits endpoint

Retrieve the current credit balance remaining in your account.

GET https://api.toriitranslate.com/api/credits

Credits cost

Requests to the credits endpoints are completely free.

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token.

Parameters

This endpoint takes no parameters.

Response headers

success boolean

Whether the request was successful.

Response body

The response content is a JSON object.

{
    "credits": 145.25
}

{
    "success": true,
    "message": "Successfully shared 10 credits with [email protected]."
}

Example code

Usage endpoint

Retrieve the per-day request counts shown in your dashboard, broken down by endpoint, for one API key, all your keys together, or your whole account.

GET https://api.toriitranslate.com/api/usage

Credits cost

Requests to the usage and keys endpoints are completely free and are not counted as usage.

Authentication

Authenticate your requests by including your API key in the Authorization header as a Bearer token. Any of your keys can read the usage of every key on your account.

Parameters

query string

Send these in the query string, such as ?days=90&scope=api.

days integer optional

How many days to return, ending today (UTC).

Default: 30
Range: 1 to 730

scope string optional

What the counts cover.

Default: key
Values: keyOne key: the one making the request, or the one in key_id
apiEvery key on your account added together, revoked ones included
accountEverything on your account: the website, extension and apps as well as the API

key_id string optional

Reads another key on your account instead of the one making the request, including a revoked one. Find ids with the keys endpoint, or next to each key at the bottom of this page. Works only with scope key, which it sets for you.

Format: 16 hex characters

by_key boolean optional

Also splits the totals and each day by key, under by_key. Works only with scope api.

Default: false

Response headers

success boolean

Whether the request was successful.

Response body

The response content is a JSON object. With scope key or api, each count is one successful request, under the endpoint it was sent to. With scope account, each step counts on its own, so one translated image adds an OCR and a translation, and an api block counts the steps that came through the API. The byok counts are the subset of those requests that ran on your own provider key rather than Torii's; a BYOK request that fell back to Torii's model is not counted as BYOK. The credits block holds the credits those requests spent, by endpoint.

scope string

The scope the counts cover.

key object · keys array

With scope key, the key the counts are for. With scope api, every key on your account. Each one has the fields the keys endpoint returns.

totals object

Request counts summed over the whole period. With by_key, its by_key holds the same counts for each key id that was used in the period.

usage array

One entry per day, oldest first, with the same counts as totals plus its date (YYYY-MM-DD, UTC). With by_key, each day's by_key holds only the keys used that day.

{
    "scope": "api",
    "keys": [
        { "id": "3f9a1c2b7d4e5f60", "name": "Discord bot", "active": true, ... },
        { "id": "8b02e47c19d3a6f5", "name": "Old server", "active": false, ... }
    ],
    "totals": {
        "translate": 120, "ocr": 40, "inpaint": 15, "typeset": 0, "colorize": 0, "total": 175,
        "byok": { "translate": 100, "ocr": 0, "inpaint": 5, "typeset": 0, "colorize": 0, "total": 105 },
        "credits": { "translate": 21.5, "ocr": 40, "inpaint": 0.3, "typeset": 0, "colorize": 0, "total": 61.8 }
    },
    "usage": [
        {
            "date": "2026-09-24",
            "translate": 12, "ocr": 4, "inpaint": 1, "typeset": 0, "colorize": 0, "total": 17,
            "byok": { "translate": 10, "ocr": 0, "inpaint": 1, "typeset": 0, "colorize": 0, "total": 11 },
            "credits": { "translate": 2.4, "ocr": 4, "inpaint": 0.02, "typeset": 0, "colorize": 0, "total": 6.42 }
        },
        ...
    ]
}

Response body

The response content is a JSON object.

keys array

Every key on your account, newest first, except deleted ones, with these fields:

id string

The key's id. Pass it as key_id to the usage endpoint.

name string or null

The name you gave it. Keys created before keys had names have none.

display_key string

The key with its middle hidden.

active boolean

False once the key is revoked.

created_at · revoked_at string or null

When the key was created and revoked, as ISO 8601 timestamps in UTC.

last_used string or null

The day (YYYY-MM-DD, UTC) of the key's last successful request.

current boolean

True for the key that made this request.

limit integer

How many active keys an account can have at once.

{
    "keys": [
        {
            "id": "3f9a1c2b7d4e5f60",
            "name": "Discord bot",
            "display_key": "sk_torii_Xb3kQ************9fLw",
            "active": true,
            "created_at": "2026-10-01T09:12:44+00:00",
            "revoked_at": null,
            "last_used": "2026-10-09",
            "current": true
        },
        ...
    ],
    "limit": 10
}

Example code

Manage your API keys

Give each app its own key. You'll see what each one uses, and you can revoke one without touching the others.

Torii Image Translator API

Get started in minutes

Sign up and get your key

Top up your credits

Make your first request

Limits and rate throttling

Standard rate limit

Image and file limits

Handling limit errors

API reference

Typeset endpoint

Credits cost

Build your request

Authentication

Parameters

Response headers

Response body

Example code

Translate endpoint

Credits cost

Build your request

Authentication

Parameters

Response headers

Response body

Response fields

Example code

OCR endpoint

Credits cost

Authentication

Parameters

Response headers

Response body

Response fields

Example code

Inpaint endpoint

Credits cost

Authentication

Parameters

Response headers

Response body

Example code

Colorize endpoint

Credits cost

Authentication

Parameters

Response headers

Response body

Errors

Example code

Credits endpoint

Credits cost

Authentication

Parameters

Parameters

Response headers

Response body

Example code

Usage endpoint

Keys endpoint

Credits cost

Authentication

Parameters

Parameters

Response headers

Response body

Response body

Example code

Manage your API keys

Dashboard