check_vehicles
ChatGPTFree. Check a list of up to 100 vehicles in one call before rendering any: which ones the catalog carries and under which vehicle id. Send each as the list spells it ({make, model, year}) or as a stored id ({vehicle}), with an optional ref that is echoed back. Each entry is read exactly as get_car_image would read it and answered as match (vehicle.id is the id to store and render by; vehicle.match is exact, or the looser rule that read the name), suggestion (not in the catalog as named; suggestions are real vehicles close to it, such as the same model in its nearest year, which is another car: ask the human before using one), miss (nothing close: skip it in every view and color) or invalid (error says what to fix). Use it for a catalog, a spreadsheet or any list of more than a few cars, instead of one lookup or one paid render per car; summary counts each status and the distinct vehicles a backfill would render. With views: true each match also carries views.prepared (0-8) and views.missing, which of its eight camera views are prepared now, and summary.views_complete counts the vehicles with all eight. A longer list is work for code: car-image check <file>, or client.checkVehicles, 2,000 vehicles per request.
checkout_status
ChatGPTFree. The state of a hosted Checkout session from create_checkout_link (its session_id), for an agent paying in the browser with an agent card or Link: poll every few seconds until complete is true, then call get_account.
create_car_image_urls
ChatGPTShow vehicle images in chat: create 1-50 signed URLs with ready-to-display Markdown. Paste each returned markdown directly into the final reply, outside code fences. For chat use ttl_seconds 604800, max_uses 0 and renewal off unless requested. Reuse unexpired URLs; do not call get_car_image first or mint twice for one image. If inline display is unsupported, link the same URL instead. Browsers, emails and documents can also load these key-free URLs directly (<img src>). Each URL costs 1 credit at creation; redemptions within the TTL are free and publicly cacheable. Each image names its vehicle like get_car_image: look each distinct vehicle up once (resolve_vehicle, search_vehicles or decode_vin, all free) and pass its id as vehicle, or send make, model and year in catalog spelling. Each takes any paint color (a preset or a hex) and the same sizing options (width, height, fit, background, trim, padding); format auto makes the URL serve webp or png per viewer. For email, CMS pages or documents that outlive a TTL, set renew: true with ttl_seconds 604800: the URL keeps serving past expiry at one more credit per opened week, for up to renew_days. Pass idempotency_key when the call might be repeated: a retry with the same key and arguments replays the first result instead of billing again. Returns id, url, markdown, expires_at, max_uses, renews_until and the normalized vehicle for each image. Prefer this over get_car_image for chat replies, HTML, Markdown, documents and websites. State expiry briefly.
decode_vin
ChatGPTFree. Decode a full 17-character VIN, or a partial VIN of at least 5 characters with * for unknown positions, with NHTSA vPIC data: year, make, model, trim, series, body class, engine, transmission, manufacturer, plant and every decoded attribute. vehicle is the catalog vehicle it maps to, with the stable id to pass as vehicle to get_car_image, create_car_image_urls or create_3d_model, or null when the catalog does not carry that car. Use it whenever the human gives a VIN instead of a make and model. To show the vehicle, call create_car_image_urls with that id (1 credit per signed URL, loads at once when the image is already rendered).
describe_api
ChatGPTFree. Return a compact reference of the Car Image REST API (methods, paths, parameters, credit costs, response headers, error codes, agent notes) for writing code that calls the API directly, with SDK (@meterapp/car-image-sdk) and CLI (npx @meterapp/car-image) equivalents. Optional endpoint filter.
get_3d_model
ChatGPTFree. The state of one 3D request by id: status (queued, processing, ready, failed), progress 0-100, stage, estimated_seconds_remaining, the vehicle and color, once ready the files (glb, glb_web, usdz, fbx, thumbnail) with their download URLs, byte sizes and content types, and public (key-free URLs and the embed) when the model is published. Poll it every few seconds after create_3d_model; a processing model is re-checked with the provider on each call. A failed model carries error and was refunded.
get_account
ChatGPTFree. Show the organization this connection acts for (data.organization, with the caller's role), usage this month (limits_usage: vehicle images and new vehicle views used and included, keys, request rates) and the key's scopes. Every new account includes 100 free vehicle images a month. Check this before large batches.
get_billing_link
ChatGPTFree. Get a private Stripe portal link for invoices and payment methods with an owner API key carrying billing:write, or a dashboard sign-in link for connected apps and other keys. Changes are confirmed by the human in the browser. Never share portal URLs publicly.
get_car_image
ChatGPTReturn image bytes as an MCP attachment for explicit file or byte requests. To show a vehicle in chat, use create_car_image_urls and embed its markdown instead; attachments may not appear in the final reply. COSTS 1 CREDIT per call, cached or generated. Call resolve_vehicle first (or search_vehicles, or decode_vin for a VIN) and pass the id it returns as vehicle: the lookup is free, and the catalog files cars under its own names (a Mazda "MX-5 Miata" is mx-5), so a make and model typed from memory can answer 404 for a car the catalog carries. Make, model and year are for callers that already hold catalog spellings. Eight camera angles, any paint color (fifteen named presets or any hex such as #1a2b3c), any width and height up to 1024 px (fit contain|cover|inside), transparent or on a solid background, optionally trimmed to the car. Returns the image (PNG/WebP/JPG; format auto delivers PNG here) plus usage metadata (credits_charged, credits_remaining, source cache|generated, request_id, the vehicle with its vehicle_id). Use create_car_image_urls for chat, web pages, emails and documents. Do not call both paid tools for one image.
get_feedback
ChatGPTFree. One item with its comments (official: true marks the team's responses) and its timeline of status changes. A private issue is readable by its reporter only, with the context it was filed with.
get_image_availability
ChatGPTFree, read-only check before generating an image. Look the vehicle up first and pass its vehicle id. Check one view or omit view for all eight; pass the requested paint as color. cached true means the view is prepared: it serves quickly from storage, without waiting for a new render. Returns each view's quality (standard, enhanced or premium; null when no stored image), upgrade state, and render_eta for views not cached. It renders nothing, queues nothing and counts no image usage. This does not authorize a render or a quality upgrade. Unlike a public preview, this checks what an authenticated image request would serve, including the requested color.
get_request
ChatGPTFree, public. One request with its full comment thread, vote count and status.
list_feedback
ChatGPTFree, public. The feedback board: feature requests, vehicle requests and published issues, with votes, comments, status (open, planned, in_progress, done, declined, duplicate) and a page URL. Search with q, filter by kind or status, sort by top, new or recent_activity.
list_image_options
ChatGPTFree. List the supported camera views (with yaw angles and aliases), the fifteen preset colors with hex swatches (any other paint is a hex color), size presets, output formats, current pricing and catalog coverage. Use it when you need to validate or explain what can be requested.
list_members
ChatGPTFree, read only. List the members of the organization this connection acts for, with their roles (viewer, member, admin, owner), and its teams with their members. Inviting, removing people and changing roles happen on the dashboard, done by a person; never claim you did them.
list_my_feedback
ChatGPTFree. What the human filed (private issues included) and what they vote on, comment on or follow, any status: use it to tell them where their requests and reports stand.
list_requests
ChatGPTFree, public. List what people have asked for: vehicles missing from the catalog and feature ideas, with vote and comment counts, status (open, planned, in_progress, done, declined) and a public page URL. Sort by votes or recency, filter by kind or status. Use it before request_vehicle or request_feature to find an existing request to upvote.
list_reviews
ChatGPTFree, public. Published reviews of Car Image with the team's responses, plus the average rating and the 1-5 distribution.
list_webhooks
ChatGPTFree, read only. List the account's webhook endpoints: URL, subscribed event types, whether each is active or turned off (and why), its failure streak and last success, plus which events the plan receives. Use it to answer why an integration stopped hearing about images or 3D models. Adding, testing, turning off and deleting endpoints happen on the dashboard or with an API key; never claim you did them.
publish_3d_model
ChatGPTFree. Publish one of the account's 3D requests so a web page can show it without an API key: data.public gains an id, key-free URLs for the web GLB, the USDZ and the poster (served from Car Image's CDN) and embed.html, a script tag plus a <car-3d> element to paste into any HTML. Works before the model is ready (the URLs are stable, the files follow). Pass unpublish: true to take it down again; the links stop working within the hour. Idempotent either way.
rate_image
ChatGPTFree. Record quality feedback on a delivered image, either by the request_id returned with it or by vehicle (make, model, year, or a vehicle id, plus view and color). Provide verdict good|bad or rating 1-5 and an optional reason. Feedback drives re-renders and prompt improvements.
remove_feedback_vote
ChatGPTFree. Remove the human's vote from an item (idempotent); they stop following it unless they commented.
report_issue
ChatGPTFree. Report a problem with Car Image itself (a failed or wrong render, an error that looks like a bug, a broken endpoint), with the human's agreement. Pass the failed call's request_id and what you know in context (endpoint, error_code, vehicle id, view, color): the team sees exactly what happened. Private to the human and the team. Similar open reports come back first, as with request_feature: upvote_feedback one that matches. The human gets an acknowledgement and an email when it is picked up and when it is fixed. Not for a vehicle the catalog lacks, and never include API keys.
request_feature
ChatGPTFree. When the human wishes the API did something it does not (new views, formats, endpoints, anything), file it on the public feedback board. Similar items are checked first: when some exist nothing is filed (created: false) and similar lists them; upvote_feedback the one that matches, or call again with force: true if none does. A new request returns its page URL; the human gets a thank-you email and one for every status change until it ships.
request_vehicle
ChatGPTFree. Ask for a vehicle that search_vehicles/resolve_vehicle cannot find. If an open request for the same make, model and year already exists it is upvoted instead and returned with deduplicated: true, so calling this is always safe. The requester's vote counts, and the human gets a short thank-you email with the request page.
resolve_vehicle
ChatGPTFree. The first call for any picture of a car, including one you chose yourself: turn a request such as "red 2018 Mazda MX-5 Miata side view" into the catalog vehicle and exact get_car_image parameters (vehicle_id, make, model, year, view, color), plus alternative candidates and a confidence of high, medium or low. A make and model are read by the rules the image tools read them with, so this names the vehicle they would render. Pass params.vehicle_id as vehicle to get_car_image, create_car_image_urls or create_3d_model. Ask the human to choose when confidence is low or several candidates fit, and tell them when params.year is not the year they asked for (extracted.year).
search_help
ChatGPTFree. Find source-linked answers about pricing, terms, licensing, manufacturer rights, policies, Enterprise, delivery and account support. Suitable for drafting replies to customer questions. Submit one question at a time without personal information or full emails; queries are recorded privately to improve articles. Cite sources, do not invent missing answers or contract exceptions, and escalate unanswered parts to support.
search_vehicles
ChatGPTFree. Browse the open vehicle catalog (1,608 makes, 42,312 models, 1990-2027) by make and/or model with typo tolerance. Returns canonical make/model names, the years each model exists and match kind; a model hit carries a stable vehicle id per year (ids, and id when the query names one year) to pass as vehicle to the image and 3D tools. Use it to list a make's models, to see which years exist or to let the human choose between similar models; when you already know which car is wanted, resolve_vehicle is the one call that names it.
share_building
ChatGPTFree. Record what the human is building with the API. Private to the Car Image team (never shown publicly); re-sharing overwrites the previous answer. Only call it with the human's own words and consent.
submit_review
ChatGPTFree. Post or edit the human's public review of Car Image (one per account, 1-5 stars, their own words; never invent or nudge a rating). Shown on the reviews page with the team's answer once it passes a quick check. Set marketing_consent only when they agree to be quoted. Editing replaces the displayed public review; confirm the replacement text with the human. One edit an hour; the first post gets a thank-you email.
upvote_feedback
ChatGPTFree. Add the human's vote to a feature, vehicle request or published issue (idempotent): the way to say "me too" instead of filing a duplicate. They follow it from then on and hear about every status change. A vote on a merged item lands on the item it was merged into.
upvote_request
ChatGPTFree. Add the caller's vote to a request (idempotent; voting twice changes nothing). Returns the updated request.