litellm/tests/e2e/claude_code/basic_messaging_streaming
mateo-berri 3befa3afc3 test(e2e): bump claude code compat matrix tiers to sonnet-5 and opus-4-8
Anthropic and both Bedrock surfaces move their mid and large tiers from
claude-sonnet-4-6 / claude-opus-4-7 to claude-sonnet-5 / claude-opus-4-8.
The haiku-4-5 small tier is unchanged everywhere.

Vertex AI stays fully on the old tiers and Azure keeps sonnet-4-6 in its
sonnet slot (opus does bump to 4-8): live validation showed both new base
models 429 with 0 TPM quota in the suite's Vertex project/region, and the
Foundry subscription has a hard 0 TPM quota limit for Claude Sonnet 5, so
a sonnet-5 deployment cannot be created yet. test_v0_layout now encodes
the per-provider tier expectations so the pins are enforced and documented.
2026-07-15 16:47:31 -07:00
..
__init__.py test(claude_code): move the Claude Code compatibility matrix under tests/e2e (#32548) 2026-07-14 19:19:03 -07:00
test_anthropic.py test(e2e): bump claude code compat matrix tiers to sonnet-5 and opus-4-8 2026-07-15 16:47:31 -07:00
test_azure.py test(e2e): bump claude code compat matrix tiers to sonnet-5 and opus-4-8 2026-07-15 16:47:31 -07:00
test_bedrock_converse.py test(e2e): bump claude code compat matrix tiers to sonnet-5 and opus-4-8 2026-07-15 16:47:31 -07:00
test_bedrock_invoke.py test(e2e): bump claude code compat matrix tiers to sonnet-5 and opus-4-8 2026-07-15 16:47:31 -07:00
test_vertex_ai.py test(claude_code): move the Claude Code compatibility matrix under tests/e2e (#32548) 2026-07-14 19:19:03 -07:00