Building a Cost-Effective, ZDR-Compliant Code Review System with Pullfrog + Ollama Cloud

A developer connected Pullfrog, a GitHub Actions-based coding agent, to DeepSeek V4.1 Flash served through Ollama Cloud to build a repeatable, low-cost, Zero Data Retention-compliant automated code review setup. The configuration pairs Pullfrog's flat $30/month per-organization pricing with Ollama Cloud's $20/month Pro plan and DeepSeek V4.1 Flash token rates of $0.15 per million input tokens and $0.60 per million output tokens, with inference typically exceeding 150 tokens per second. The developer notes Ollama states it does not store prompts or use them for training, though inference runs in US and European regions.

Thorough code review on pull requests lets you catch bugs early in the development cycle, such as misused libraries and APIs or gaps in the logic. Fixing a bug at that stage costs far less than fixing the same bug later<sup 1</sup . Still, human review has its limits. When you're tired, for example, you might approve with a "good enough" shrug. So what can we do? Have a smart AI model with cheap tokens review the code thoroughly. AI doesn't get tired, and it doesn't get grumpy when you show it bad code. You can have it review as many rounds as it takes until you're satisfied, so problems get fixed before merge. In this article, I describe how I connected Pullfrog, a coding agent that runs on GitHub Actions, to DeepSeek V4.1 Flash, a model that Ollama serves on its cloud with Zero Data Retention ZDR <sup 2</sup , to build a setup that can run code reviews again and again at a nearly flat cost. Code review isn't something you do once and are done with. You want problematic code caught before merge, and every time the pull request changes, you want someone to check whether new problems have crept in. In other words, you want code review to look at things like these: It goes without saying that having AI do all of this burns through tokens. According to the official documentation, Claude's Code Review feature costs $15–25 per review<sup 3</sup . When every review carries a noticeable cost, you naturally start rationing how often you run it. With a sufficiently cheap AI model, on the other hand, you can iterate on the code as many times as you like without worrying about cost, and merge pull requests with more confidence. There's also the human side: asking a person to look at nearly the same code again and again feels awkward. For example, you can have AI review the code repeatedly until you're confident in it, and only then hand it over for human review. Pullfrog https://pullfrog.com/ , which I used here, is a coding agent that runs on GitHub Actions. When you open a pull request, it reads the description and the diff, reviews the code, and comments on any problems it finds. You can also have Pullfrog write commits that fix what it pointed out. Beyond code review, it can triage and label issues and take requests to fix broken CI. Pullfrog charges a flat fee regardless of the number of users $30/month per organization for GitHub organization accounts, free for personal accounts , so even large teams can use it without worrying about seat counts. Pullfrog can connect to any AI model. You can connect it to OpenAI or Claude with API keys your company already has, or to Ollama Cloud as I did here. I chose Ollama Cloud for this setup because it excels in cost and inference speed, and it supports ZDR. Ollama's Pro plan costs $20 a month and comes with a whopping $60 in credits every month. Companies with multiple users will probably go with the Team plan, which allows unlimited users who share credits $500 a month with $1,000 in credits . Of course, Ollama isn't just for code review, so credits you don't spend on code review can go to other uses. With DeepSeek V4.1 Flash as the model on Ollama Cloud, inference speed usually exceeds 150 tokens per second<sup 4</sup , so it's comfortable to use, and it's very cheap: per million tokens, $0.15 for input, $0.003 for cached input, and $0.60 for output<sup 5</sup . Since you're having it review your code, you'll probably want to know how Ollama handles your data. Automated code review sends not only the diff but also related code to the AI. That's why you'll want to confirm whether the data you send is stored or used for training before you even look at accuracy or cost. Ollama states explicitly that it does not store the prompts you send and does not use them to train models<sup 6</sup . Note, however, that inference runs in US and European regions. Depending on your company's policies, you may need to check separately whether your data is allowed to leave your country. When choosing the model, I also took into account that DeepSeek V4.1 Flash scores close to Claude Opus 5 on some benchmarks https://pc.watch.impress.co.jp/docs/news/2140010.html in Japanese . That said, benchmark scores alone don't tell you how useful a model will be for code review. Later in this article, I'll show the findings I actually got when it reviewed pull requests. First, sign up for both Pullfrog and Ollama. Next, configure Pullfrog to call Ollama's models. As of September 22, 2026, connecting Pullfrog to Ollama Cloud requires the "Custom: OpenAI-compatible endpoints" option. To use DeepSeek V4.1 Flash, enter the following settings in the Pullfrog console. | Setting | Value | |---|---| | OPENAI COMPATIBLE BASE URL | https://ollama.com/v1 | | OPENAI COMPATIBLE API KEY | An API key issued from the Ollama dashboard | | OPENAI COMPATIBLE MODEL | deepseek-v4.1-flash | | OPENAI COMPATIBLE CONTEXT | 1000000 | | OPENAI COMPATIBLE MAX OUTPUT | 384000 | Then install Pullfrog on your repository, and it will run when you open a pull request or mention @pullfrog . See Pullfrog's Getting started guide https://docs.pullfrog.com/getting-started for details. After installing Pullfrog, I had it review code without any special configuration, and it came back with findings like these: It investigated the library's code and issues before answering, and it also analyzed failures in the E2E tests already running on GitHub Actions. That shows it goes beyond code review in the narrow sense and looks at whether the code is safe to merge. The following is an example of a review comment raised by Pullfrog. The cost of the review system is the monthly Ollama and Pullfrog subscriptions plus GitHub Actions usage for running Pullfrog. When I had it review several pull requests, Pullfrog ran for about 10–20 minutes per review and consumed about $0.15 in DeepSeek V4.1 Flash credits. The estimates below assume 20 minutes and $0.15 in model credits per review. With Ollama's $20/month Pro plan and Pullfrog's free plan<sup 7</sup , the costs look roughly like this. The $60 in credits that come with Ollama's $20 Pro plan cover about 400 reviews, and after that you can pay as you go. GitHub Actions on the Free plan includes 2,000 free minutes, enough for about 100 reviews. After that, a review costs only about 0.006 USD / min 20 min = $0.12. | Number of reviews | Added cost per review | |---|---| | Up to 100 | $0 | | 100–400 | $0.12 | | 400+ | $0.27 | With Ollama's $500/month Team plan and Pullfrog's $30/month plan, the costs look roughly like this. The $1,000 in credits that come with Ollama's $500 Team plan cover about 6,700 reviews, and after that you can pay as you go. GitHub Actions on the Team plan includes 3,000 free minutes, enough for about 150 reviews. After that, a review costs only about 0.006 USD / min 20 min = $0.12<sup 8</sup . | Number of reviews | Added cost per review | |---|---| | Up to 150 | $0 | | 150–6,700 | $0.12 | | 6,700+ | $0.27 | In short, for up to roughly 100–150 reviews a month, you pay a flat cost: just the Ollama subscription at $20 on a personal account, or $530 for Ollama and Pullfrog combined on an organization account. Beyond that, each review still costs only about $0.12–$0.27. At this price, you lose more by not running thorough code reviews than by running them. This article showed how to build an automated code review setup on GitHub with Pullfrog and Ollama Cloud that you can run again and again without worrying much about cost. Using Ollama Cloud with ZDR also keeps your prompts and responses from being stored or used for training without you realizing it. If you're interested, start small with a personal repository. See, for example, "What does it mean that catching bugs in an earlier phase keeps the damage small?" https://satoru-takeuchi.hatenablog.com/entry/2026/09/20/231104 in Japanese . ↩ Zero Data Retention ZDR is a mechanism or policy under which the service provider does not retain content sent to an AI service, such as prompts and generated output, after processing completes. ↩ https://code.claude.com/docs/en/code-review https://code.claude.com/docs/en/code-review ↩ The DeepSeek V4.1 Flash tokens per second https://ollamatps.com/models/ollama/deepseek-v4.1-flash/ page on Ollama TPS shows the model's historical TPS. ↩ Note that weekdays from 12:00 to 18:00 UTC are peak hours, when token prices double. It's still cheap enough. ↩ Transparent pricing Ollama Blog https://ollama.com/blog/transparent-pricing states "Zero data retention, hosted in the US and Europe, plus Singapore for a limited set of Qwen models" and "We don't log your prompts, and we never train on your data." The privacy policy https://ollama.com/privacy also says "We do not use your inputs or outputs to train any AI models," and for cloud models, "this content is not stored beyond the time required to fulfill the request." Both as of September 2026. ↩ Pullfrog is free for open source Pullfrog Blog https://pullfrog.com/blog/free-for-open-source states "Every personal account is free, on public and private repositories." ↩ If GitHub Actions' standard runners feel too expensive, you could use a service such as Blacksmith https://www.blacksmith.sh/ , though it's available only for GitHub organizations. ↩