mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-09 08:18:12 +00:00
d82defad62
Melious is a European AI gateway fronting open-weight models, serving an OpenAI-compatible endpoint and an Anthropic-compatible Messages API from the same host. MeliousChatConfig routes /v1/chat/completions and MeliousAnthropicMessagesConfig routes /v1/messages, so both surfaces resolve from one model prefix and one MELIOUS_API_KEY instead of a hand-wired api_base per deployment. /v1/responses is inherited from the chat-completions bridge, as it is for the other openai-compatible providers Base-URL normalization lives in _get_openai_compatible_provider_info rather than in get_complete_url, where the sibling dual-compatible providers put it. Chat requests reach Melious through the OpenAI SDK path, which consumes api_base directly and never calls get_complete_url, so an override there would not have protected the route that actually runs. Resolving once at provider-info time covers the SDK path and the httpx handler both, and it lets a caller pass the bare root, the /v1 root, or a full endpoint URL for either surface The melious branch in _get_openai_compatible_provider_info binds new names and returns early instead of rebinding the function's parameters the way the surrounding branches do. That keeps the parameter-rebinding count flat against the type-discipline budget, and it matches the early-return shape already used by the aiohttp_openai branch Cost-map entries cover 17 flagship chat models. Context lengths, capability flags, and cache-read rates are taken from the provider's own model metadata endpoint rather than hand-copied. The published rates are EUR per million tokens written into LiteLLM's USD-per-token fields, which is the same convention the existing ovhcloud entries already use for OVHcloud's EUR list prices Tests cover URL normalization for every base-URL shape either surface accepts, argument-over-environment precedence for the key and the base, provider and config resolution through ProviderConfigManager, the billing-metadata strip that Melious requires on the Anthropic surface, and cost lookup against the shipped map |
||
|---|---|---|
| .. | ||
| agent_tests | ||
| audio_tests | ||
| base_sdk_tests | ||
| basic_proxy_startup_tests | ||
| batches_tests | ||
| benchmarks | ||
| code_coverage_tests | ||
| documentation_tests | ||
| e2e | ||
| enterprise | ||
| guardrails_tests | ||
| image_gen_tests | ||
| integration | ||
| litellm | ||
| litellm-proxy-extras | ||
| litellm_core_utils | ||
| litellm_utils_tests | ||
| llm_responses_api_testing | ||
| llm_translation | ||
| load_tests | ||
| local_testing | ||
| logging_callback_tests | ||
| mcp_tests | ||
| multi_instance_e2e_tests | ||
| ocr_tests | ||
| old_proxy_tests/tests | ||
| openai_endpoints_tests | ||
| otel_tests | ||
| pass_through_tests | ||
| pass_through_unit_tests | ||
| proxy_admin_ui_tests | ||
| proxy_behavior | ||
| proxy_e2e_anthropic_messages_tests | ||
| proxy_migration_tests | ||
| proxy_security_tests | ||
| proxy_unit_tests | ||
| router_unit_tests | ||
| scim_tests | ||
| search_tests | ||
| spend_tracking_tests | ||
| store_model_in_db_tests | ||
| test_litellm | ||
| unified_google_tests | ||
| vector_store_tests | ||
| windows_tests | ||
| __init__.py | ||
| _fake_openai_endpoint_server.py | ||
| _flush_vcr_cache.py | ||
| _live_test_helpers.py | ||
| _openai_record_replay_proxy.py | ||
| _vcr_conftest_common.py | ||
| _vcr_redis_persister.py | ||
| _ws_vcr.py | ||
| eval_swe_bench.py | ||
| fake_openai_endpoint.py | ||
| gettysburg.wav | ||
| large_text.py | ||
| openai_batch_completions.jsonl | ||
| pyrightconfig.json | ||
| README.MD | ||
| test_anthropic_compaction_usage.py | ||
| test_budget_management.py | ||
| test_callbacks_on_proxy.py | ||
| test_debug_warning.py | ||
| test_default_encoding_non_root.py | ||
| test_end_users.py | ||
| test_fallbacks.py | ||
| test_gpt5_azure_temperature_support.py | ||
| test_health.py | ||
| test_keys.py | ||
| test_litellm_proxy_responses_config.py | ||
| test_logging.conf | ||
| test_models.py | ||
| test_new_vector_store_endpoints.py | ||
| test_openai_endpoints.py | ||
| test_organizations.py | ||
| test_otel_thread_leak.py | ||
| test_presidio_latency.py | ||
| test_proxy_server_non_root.py | ||
| test_ratelimit.py | ||
| test_resource_cleanup.py | ||
| test_service_logger_otel.py | ||
| test_spend_logs.py | ||
| test_team.py | ||
| test_team_logging.py | ||
| test_team_members.py | ||
| test_users.py | ||
In total litellm runs 1000+ tests
[02/20/2025] Update:
To make it easier to contribute and map what behavior is tested,
we've started mapping the litellm directory in tests/test_litellm
This folder can only run mock tests.