Skip to content

Add MiniMax M3 model costs#2428

Open
octo-patch wants to merge 1 commit into
microsoft:mainfrom
octo-patch:octo/20260708-add-target-provider-model-to-existing-provider-registry-recvoLatGAbe58
Open

Add MiniMax M3 model costs#2428
octo-patch wants to merge 1 commit into
microsoft:mainfrom
octo-patch:octo/20260708-add-target-provider-model-to-existing-provider-registry-recvoLatGAbe58

Conversation

@octo-patch

Copy link
Copy Markdown

Reason: add target provider/model to existing provider registry

Summary

  • Add MiniMax M3 cost metadata to the GraphRAG LLM model cost registry.
  • Include cache-read pricing, 1M context metadata, and a regression test for the registry entry.

Test plan

  • git add -A -N && git diff HEAD | grep -E "$SECRET_RE" (no matches)
  • uv sync --all-packages
  • PYTHONPATH="/root/octopatch-4/work/repos/microsoft_graphrag/packages/graphrag-llm:/root/octopatch-4/work/repos/microsoft_graphrag/packages/graphrag-cache:/root/octopatch-4/work/repos/microsoft_graphrag/packages/graphrag-common:$PYTHONPATH" uv run pytest tests/integration/language_model/test_factory.py -q
  • uv run ruff check packages/graphrag-llm/graphrag_llm/model_cost_registry/model_cost_registry.py tests/integration/language_model/test_factory.py

Register MiniMax M3 pricing metadata so GraphRAG can calculate usage costs for the new LiteLLM provider/model combination.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
@octo-patch octo-patch requested a review from a team as a code owner July 9, 2026 07:11
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant