Randika Prasad

Hi, I'm Randika.

I keep your AI features working.

I'm an independent developer who handles model migrations, bug fixes and ongoing maintenance for apps built on any major AI provider: OpenAI, Claude, Gemini, Azure OpenAI, Vertex AI and Amazon Bedrock. When a provider retires a model, I find what breaks and move you to the replacement.

A laptop showing code on a wooden desk, next to a jade plant and a coffee cup, in warm natural light
Heads up

Three model retirements are coming, across three providers.

  1. Nov 30, 2026

    Claude Sonnet 4.5 retires

    Anthropic retires claude-sonnet-4-5-20250929 (and claude-sonnet-4-5) on the Claude API. After that, requests to it fail. Recommended replacement: claude-sonnet-5-5.

    Anthropic: model deprecations
  2. Dec 1, 2026

    Gemini 2.5 Pro and Flash are routed to newer models

    On the Gemini API, requests to gemini-2.5-pro are routed to gemini-3.8-flash, and requests to gemini-2.5-flash to gemini-3.5-flash-lite, billed at those models' rates. Google says to review the breaking API changes first.

    Google: Gemini API deprecations
  3. Jan 14, 2027

    GPT‑4o and GPT‑4.1 shut down

    OpenAI shuts down GPT‑4o, GPT‑4o mini, GPT‑4.1 and GPT‑4.1 mini in the OpenAI API. After that, requests to them fail. Recommended replacement: gpt-6-luna.

    OpenAI: deprecations

After these dates, code that still names these models fails or quietly runs on a different model. I can help you migrate before then: I find every place your code depends on them, move it to the replacement, and check that it still works.

Services and prices

Every price is fixed and agreed before I start, and you pay after delivery.

Migration off GPT-4o and GPT-4.1

Audit

$49

I find every place your code depends on a retiring model and send you a report.

1–2 days

Migration + testing

$299

Everything in Migration, plus I compare old vs new model outputs using your API key.

3–5 days

Other help

AI app bug fixes

I fix bugs in apps that use the OpenAI, Claude or Gemini APIs, like failing tool calls, API errors and broken AI-built apps.

Python · JavaScript/TypeScript · Go

Price and time quoted per issue

from $49

Monthly maintenance

I keep your AI features working as models get deprecated. I watch provider deprecation notices, scan your code with luna-check, and send fixes before anything breaks.

$99/month

What you get

Plain-language results you can read, check and keep.

Audit

A report listing every file and line that depends on a retiring model, plus the hidden problems (tiktoken, temperature, tool calls) and what to change.

Migration

A pull request with the code changes and a MIGRATION.md that explains what changed, why, every file and line touched, and what was left alone on purpose.

Testing

Side-by-side results from the old and new model, run with your API key, so you can see the difference before you merge.

Real sample report MIGRATION.md Basic-Rag: gpt-4o-mini → gpt-6-luna From my Basic-Rag fork, migration-notes branch. Shows the format I use for every migration. Read it on GitHub →

What breaks

Changing the model name isn't enough. These are real problems I found while migrating open-source projects to gpt-6-luna, OpenAI's recommended replacement for gpt-4o-mini.

Tool calls need reasoning_effort: "none"

gpt-6-luna is a reasoning model. OpenAI's model page says Chat Completions supports function calling only with reasoning_effort set to "none". Otherwise, tool calls need to move to the Responses API.

tiktoken crashes

tiktoken.encoding_for_model("gpt-6-luna") raises KeyError, in both tiktoken 0.7.0 and 0.14.0. Code that counts tokens breaks the moment you rename the model.

temperature has to go

OpenAI's migration guide says to omit temperature, top_p and top_logprobs when moving to its newest reasoning models. It's often hidden in a shared client that always sends it.

app.pyyoutube_transcription_api, PR #2
    # Initialize tokenizer-   tokenizer = tiktoken.encoding_for_model("gpt-4o-mini")+   try:+       tokenizer = tiktoken.encoding_for_model(OPENAI_MODEL)+   except KeyError:+       tokenizer = tiktoken.get_encoding(FALLBACK_ENCODING)  # "o200k_base"
The real fix from this pull request: try the new model name first, and if tiktoken doesn't know it, fall back to o200k_base, the encoding gpt-4o-mini used. Chunk sizes stay the same.
terminal
$ luna-check youtube_transcription_apiluna-check 0.2.0: scanned 2 file(s) in youtube_transcription_api app.py  line 43  HIGH  LC002  tiktoken.encoding_for_model() raises KeyError for gpt-6-luna      Called with "gpt-4o-mini". tiktoken has no entry for "gpt-6-luna", so after the switch this raises KeyError (checked with tiktoken 0.7.0 and 0.14.0).      Fix: Catch the error and fall back to get_encoding("o200k_base"), the encoding tiktoken uses for gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini.      Source: https://github.com/openai/tiktoken/blob/main/tiktoken/model.py  line 73  HIGH  LC001  Model shuts down on Jan 14, 2027      "gpt-4o-mini" points to the dated snapshot(s) gpt-4o-mini-2024-07-18, which shut down on Jan 14, 2027. Replace it with "gpt-6-luna".      Fix: Use "gpt-6-luna" (or read the model name from config).      Source: https://developers.openai.com/api/docs/deprecations Found 2 high, 0 low in 1 file(s). Need help migrating? github.com/prasadrandika
Real output from luna-check 0.2.0, run on the original code of youtube_transcription_api, before my fix. It finds both problems the fix above solves.

Check your code

Paste Python, JavaScript/TypeScript or Go code, or a config file (.env, YAML, JSON or TOML), and click Check. It runs the same 6 rules as luna-check 0.4.1, ported to JavaScript, and knows the retired and retiring models of OpenAI, Anthropic, the Gemini API, Vertex AI, Azure OpenAI and Amazon Bedrock.

Your code never leaves your browser. The check runs on this page and nothing is uploaded.

These rules catch the problems I've seen most in real migrations. They're not a full review: a clean result means none of these patterns were found, not that the code is ready.

Try it yourself

luna-check is free and open source (MIT). Run it on your own project to see what will break. It needs Python 3.9 or newer and Git.

terminal
pip install git+https://github.com/prasadrandika/luna-check@v0.4.1luna-check path/to/your/project

If it finds something and you'd like help fixing it, send me the output.

My work so far

Real migration work on open-source projects. Statuses are as they stand today.

How it works

Simple and low-risk for you.

  1. Email meTell me your stack: language, framework, and how you call the model API.
  2. Free quick checkI reply with a free quick check and a fixed price.
  3. I do the workAudit, pull request or fix, depending on what you picked.
  4. You pay afterYou pay after delivery, once you've seen the result.

Questions

Is my code safe?

Yes. I only need read access to your repository, or a zip of the code. I never store your API keys, and I'm happy to sign an NDA.

What access do you need?

Read access to the repository (or a zip) is enough for an audit, a migration or a bug fix. For Migration + testing, I also run the old and new model with your API key so I can compare outputs.

What if the fix doesn't work?

I fix it at no extra cost.

How do I pay?

PayPal or Payoneer, after delivery.

What timezone are you in?

Sri Lanka (UTC+5:30). I reply within 24 hours.

About me

I'm Randika Prasad, an independent developer in Sri Lanka. I focus on one thing: keeping AI features working when models, APIs and libraries change underneath them. I write about what I find and build small tools like luna-check from it.

Let's keep your app working.

Send me a short note about your stack. I prefer email or chat over calls, and I'll get back to you with a quick check and a fixed price.

prasadrandika618 [at] gmail.com