chore: more reliable models for testing

[njbrake]

Description

In order to not get rate limited switching off the free tier for openrouter, making some tweaks to other providers too.

Well, I didn't get this to 100% reliable, but at least it's more reliable than it was before. I'll merge this and leave it to future work to further improve test resiliancy.

PR Type

🆕 New Feature 🐛 Bug Fix 💅 Refactor 📚 Documentation 🚦 Infrastructure ## Relevant issues

Checklist

• I have added unit tests that prove my fix/feature works
• New and existing tests pass locally
• Documentation was updated where necessary
• I have read and followed the contribution guidelines```

[codecov]

Codecov Report

❌ Patch coverage is 33.33333% with 16 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/any_llm/providers/minimax/utils.py	31.25%	11 Missing ⚠️
src/any_llm/providers/minimax/minimax.py	37.50%	5 Missing ⚠️

Files with missing lines	Coverage Δ
src/any_llm/providers/minimax/minimax.py	50.00% <37.50%> (-50.00%)	⬇️
src/any_llm/providers/minimax/utils.py	31.25% <31.25%> (ø)

... and 41 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.