# CraterView.ai > Image restoration and upscaling, over an HTTP API and in the browser. Removes > compression artifacts and noise, and enlarges up to 4x, drawing fine detail at the new > size. Motion blur and missed focus are not removed: detail is drawn onto the blur, so > check anything that has to be faithful. The models in service are listed by the API. Work can be run in the browser with no signup and no card, or through the API with a key. Nothing needs paying for to run: there is no cap on how much a free account may run, and its work waits on shared community capacity. Credits and subscriptions move work onto paid compute that scales with demand. Credits do not expire. ## API - [OpenAPI specification](https://api.craterview.ai/openapi.json): every endpoint, parameter and response, complete and current. Start here to call the API. - [Browsable API reference](https://api.craterview.ai/docs): the same specification, rendered. Every model publishes its own price and its own parameter schema from the API itself, and a client should read them from there rather than from any page. The specification describes that endpoint, and it answers without an API key — the one `/v1` route that does; every other needs one. Official clients: `craterview` on PyPI and `craterview` on npm. ## MCP - [MCP endpoint](https://mcp.craterview.ai/mcp): CraterView.ai as an MCP server, over Streamable HTTP. Add it in Claude or any MCP client and authorize once; after that the assistant enhances images itself. Two tools: `enhance_image`, which takes an image URL or inline base64 and returns a link to the result, and `get_job`, which collects work that was still running. ## Pages - [Overview and pricing](https://craterview.ai/): What the platform does, what it costs, and a before/after you can drag. - [Guides](https://craterview.ai/guides): What image enhancement recovers, where it is used, and how to run it yourself. - [Terms and Conditions](https://craterview.ai/terms): The terms and conditions: what the service does, what the output is, what may be sent to it. - [Privacy](https://craterview.ai/privacy): What is stored, for how long, and what is never used for training. - [The Run Agent: from prompt to model settings to code](https://craterview.ai/guides/run-agent): Tell the Run Agent what you need, watch its proposal land on the workspace's own controls, change what you like, and copy the same run as Python, TypeScript or curl. - [Enhance and binning: enlarging a noisy photo](https://craterview.ai/guides/enhance-and-binning): When to set binning on Enhance: what each square takes out, of grain and of fine detail, on a reception at ISO 12800 and on a clean suit, and when to leave it off. - [CraterView.ai, Topaz Labs and Clarity AI compared](https://craterview.ai/guides/upscalers-compared): Twelve photographs enlarged four times by CraterView.ai, Topaz Labs and Clarity AI, six at high ISO denoised by CraterView.ai and Topaz Labs, the same region side by side, and what each costs. - [Event photography: crops, prints and low light](https://craterview.ai/guides/photo-op): A graduation, a marriage certificate, a 2004 wedding printed at 30 inches and a reception at ISO 12800: cropping in, enlarging for print, what Enhance and Denoise do with noise, and what they don't. - [Restoring historical photos](https://craterview.ai/guides/historical-photos): Einstein in 1921, Tesla's laboratory, Apollo 11 — which of the two models to send an archival photograph to, the parameters that change the result, and what to check. - [Your first API call, in three requests](https://craterview.ai/guides/your-first-api-call): Ask for somewhere to put the file, upload the bytes, submit the job — in curl, Python and TypeScript, with the parts that usually go wrong. - [Craters and plains](https://craterview.ai/guides/crater-view): Twelve landing sites, each photographed twice by the same camera at two resolutions — what a 2× enhancement recovers, what it draws that isn't there, and how we prepared the images. - [A professional headshot from a snapshot](https://craterview.ai/guides/professional-headshots): Turn a phone snapshot into a studio-style headshot for LinkedIn, a CV or a team page — which photo to start from, the three looks, and what to check before you use it. - [Checking images for content and AI generation](https://craterview.ai/guides/content-and-synthetic-checks): Flag images that may break a content policy and tell photographs from generated images, free in the workspace and through the API. - [Bit depth, colour profiles and file formats](https://craterview.ai/guides/bit-depth-colour-and-formats): Bits per channel, transfer curves, colour profiles and phone HDR, what each format holds, when not to use auto, and what to keep for the web, print, an archive and science. - [Who we are and what we do](https://craterview.ai/guides/who-we-are): CraterView.ai is a Canadian startup building image enhancement and restoration models. - [Credits and subscriptions explained](https://craterview.ai/guides/credits-subscriptions): How the free community queue works, and what credits and subscriptions add when you need more than it gives. - [Connect an assistant to the CraterView.ai MCP server](https://craterview.ai/guides/connect-an-assistant): CraterView.ai as an MCP server — add one address to Claude or any MCP client, paste a code from your dashboard, and your assistant can enhance, denoise and restore photos. - [Image enhancement and restoration skills for your assistant](https://craterview.ai/guides/agent-skills): How to install and use the CraterView.ai skills in Claude Code and similar agents.