* test: modernize models used in CircleCI e2e test suites
Replaces obsolete models (gpt-4o, gpt-4o-mini, gpt-3.5-turbo,
claude-3-5-sonnet-20240620, claude-sonnet-4-20250514) with current
equivalents across the e2e_openai_endpoints and
proxy_e2e_anthropic_messages_tests CircleCI jobs.
- gpt-4o -> gpt-5.5 (responses API e2e tests)
- gpt-4o-mini -> gpt-5-mini (websocket responses, oai_misc_config)
- gpt-4o-mini-2024-07-18 -> gpt-4.1-mini-2025-04-14 (fine-tuning,
still actively fine-tunable)
- gpt-4 / gpt-3.5-turbo target_model_names example -> gpt-5.5 /
gpt-5-mini
- bedrock claude-3-5-sonnet-20240620 batch entry -> haiku-4-5-20251001
(also aligning oai_misc_config model_name with what
test_bedrock_batches_api.py actually requests)
- bedrock claude-sonnet-4-20250514 (deprecated, retires 2026-06-15)
-> claude-sonnet-4-5-20250929
* test: point bedrock-claude-sonnet-4 alias at Sonnet 4.6, not 4.5
Greptile/Cursor flagged that after the previous commit, the
bedrock-claude-sonnet-4 alias collided with bedrock-claude-sonnet-4.5
(both pointed to claude-sonnet-4-5-20250929). Rename to
bedrock-claude-sonnet-4.6 and point it at the Sonnet 4.6 Bedrock ID
(us.anthropic.claude-sonnet-4-6, already in the litellm model
registry) so the alias name matches the underlying model version.
* test: modernize models across remaining CI-mounted configs & tests
Expands the modernization sweep to all CircleCI-mounted proxy configs
and to test directories where the model literal is a fixture/route key
(not the test's subject).
Config changes:
- proxy_server_config.yaml: bump gpt-3.5-turbo / gpt-3.5-turbo-1106 /
gpt-4o / gemini-1.5-flash / dall-e-3 underlying models; rename
gpt-3.5-turbo-end-user-test alias to gpt-5-mini-end-user-test; bump
text-embedding-ada-002 underlying to text-embedding-3-small. User-
facing aliases (gpt-3.5-turbo, gpt-4, text-embedding-ada-002, etc.)
preserved for backward compatibility with tests.
- simple_config.yaml, otel_test_config.yaml, spend_tracking_config.yaml:
bump gpt-3.5-turbo underlying to gpt-5-mini.
- pass_through_config.yaml: claude-3-5-sonnet / claude-3-7-sonnet /
claude-3-haiku entries replaced with claude-sonnet-4-5 / claude-
haiku-4-5 / claude-opus-4-7.
- oai_misc_config.yaml: align alias name with the gpt-5-mini rename.
Test changes (proactive: claude-sonnet-4-20250514 / claude-opus-4-
20250514 retire 2026-06-15):
- tests/llm_translation/test_anthropic_completion.py: bump 3 references
+ paired Vertex AI ID to claude-sonnet-4-5.
- tests/llm_translation/test_optional_params.py: bump 2 references.
- tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py
and test_bedrock_anthropic_messages_test.py: bump router fixtures
using the deprecated model IDs.
- tests/pass_through_unit_tests/base_anthropic_messages_tool_search_test.py:
modernize docstring examples.
- tests/test_end_users.py: update references to renamed alias.
* test: modernize placeholder model literals in router_unit_tests
Mass replace_all on fixture/placeholder model literals across the
router_unit_tests/ suite (model name is a routing key / label, not the
test subject). Sub-agent sweep so far — additional commits will follow
for logging_callback_tests/, enterprise/, top-level tests/test_*.py,
and other CI-mounted dirs.
Mappings applied:
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 / claude-3-opus-20240229 /
claude-3-haiku-20240307 / claude-3-5-sonnet-20240620 ->
claude-sonnet-4-5-20250929 / claude-opus-4-7 /
claude-haiku-4-5-20251001 as appropriate
Explicitly preserved:
- gpt-4o-mini-* variants (transcribe, tts, etc.) where they're current
- gpt-4-turbo / gpt-4-vision-preview / gpt-4-0613 (subject literals)
- JSONL batch body literals
- Mock LLM response model fields (must match upstream)
- Fake/mock identifiers
* test: modernize placeholder model literals across remaining CI suites
Sub-agent sweep across logging_callback_tests/, guardrails_tests/,
enterprise/, pass_through_unit_tests/, otel_tests/,
llm_responses_api_testing/, batches_tests/, spend_tracking_tests/,
litellm_utils_tests/, unified_google_tests/, and a few top-level
tests/test_*.py files where the model literal is a fixture or
placeholder (router model_list, mock standard logging payload, mock
callback data) rather than the test's subject.
Mappings applied (see scope notes below):
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5.5 (corrected from initial gpt-5 — bare gpt-5
is not a valid OpenAI alias; only gpt-5.5 / gpt-5.4 / gpt-5.2-codex
/ gpt-5-mini exist)
- gpt-4o-mini (bare) -> gpt-5-mini
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 -> claude-sonnet-4-5-20250929
- claude-3-opus-20240229 -> claude-opus-4-7
- claude-3-haiku-20240307 -> claude-haiku-4-5-20251001
- claude-3-5-sonnet-20240620/20241022 -> claude-sonnet-4-5-20250929
- claude-3-7-sonnet-20250219 -> claude-sonnet-4-6
- gemini-1.5-flash -> gemini-2.5-flash
- gemini-1.5-pro -> gemini-2.5-pro
Explicitly preserved (not modernized):
- llm_translation/ tests where model is the SUBJECT (provider-specific
translation/transformation logic). Only the deprecated 20250514
references were already bumped in a prior commit.
- Cost-calc / tokenizer subject tests in test_utils.py (skip-ranges
documented by the sub-agent).
- Bedrock model IDs in test_health_check.py path-stripping tests.
- JSONL batch request bodies and mock LLM response bodies (must match
upstream literal).
- Langfuse expected-request-body JSON fixtures (cost values are exact-
match-asserted; changing the model would shift response_cost).
- gpt-3.5-turbo-instruct (text-completion endpoint; no modern OpenAI
equivalent).
- Top-level tests calling the proxy through user-facing aliases
(gpt-3.5-turbo, gpt-4, text-embedding-ada-002, dall-e-3) — aliases
in proxy_server_config.yaml stay; only the underlying model was
bumped.
- tests/test_gpt5_azure_temperature_support.py (the test's whole point
is model-name handling).
- Fake / mock / openai/fake identifiers.
Notable side fixes:
- test_spend_accuracy_tests.py: UPSTREAM_MODEL now matches what
spend_tracking_config.yaml's proxy actually routes to (gpt-5-mini),
resolving a latent inconsistency.
- proxy_server_config.yaml: bare `gpt-5` alias renamed to `gpt-5.5`
(bare gpt-5 is not a valid OpenAI alias).
- test_batches_logging_unit_tests.py: explicit_models list entries
kept distinct (gpt-5-mini + gpt-5.5) after bulk rename.
* test: fix CI failures from model modernization sweep
CI surfaced 4 categories of regression from the bulk modernization:
1. Azure deployment names are customer-specific. Reverted:
- tests/litellm_utils_tests/test_health_check.py: azure/text-
embedding-3-small -> azure/text-embedding-ada-002 (the CI Azure
account does not have a text-embedding-3-small deployment).
- tests/logging_callback_tests/test_custom_callback_router.py:
same revert for two router fixtures driving aembedding.
2. gpt-5 family does not accept temperature != 1. Tests that pass a
custom temperature swapped from gpt-5-mini to gpt-4.1-mini (modern
non-reasoning OpenAI mini that still accepts temperature/logprobs):
- tests/logging_callback_tests/test_datadog.py
- tests/logging_callback_tests/test_langsmith_unit_test.py
- tests/logging_callback_tests/test_otel_logging.py
3. proxy_server_config.yaml's gpt-3.5-turbo-large alias was routing to
gpt-5.5 (a reasoning model that rejects logprobs). The proxy test
tests/test_openai_endpoints.py::test_chat_completion_streaming
exercises logprobs/top_logprobs through that alias. Bumped the
underlying model to gpt-4.1 (non-reasoning, still modern).
4. tests/logging_callback_tests/test_gcs_pub_sub.py asserts against a
pinned JSON fixture (gcs_pub_sub_body/spend_logs_payload.json) with
hardcoded model="gpt-4o" and a model-specific spend value. Reverted
the litellm.acompletion calls in the test to model="gpt-4o" so the
fixture's exact-match assertions still hold.
5. tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py:
anthropic.messages.create routing to openai/gpt-5-mini returned an
empty content[0] with max_tokens=100 (reasoning-token consumption).
Swapped to openai/gpt-4.1-mini.
* test: fix Assistants API model + 2 cursor[bot] review nits
1. pass_through_unit_tests/test_custom_logger_passthrough.py: gpt-5.5
isn't accepted by the /v1/assistants endpoint
("unsupported_model"). Switch to gpt-4.1-mini (modern, Assistants-
API-supported, non-reasoning).
2. example_config_yaml/pass_through_config.yaml: the previous sweep
bumped the claude-3-7-sonnet alias to claude-opus-4-7, which is a
tier change (Sonnet -> Opus). Map to claude-sonnet-4-6 to keep the
Sonnet tier intact. (Cursor bugbot review.)
3. example_config_yaml/simple_config.yaml: model_name was left as
gpt-3.5-turbo while the underlying was bumped to gpt-5-mini, which
muddles the "simple" example. Make both sides gpt-5-mini so the
most basic example is a straight 1:1 mapping again. (Cursor bugbot
review.)
* fix: revert gpt-4/gpt-3.5-turbo alias underlying to non-reasoning models
tests/test_openai_endpoints.py::test_completion calls the proxy alias
"gpt-4" with temperature=0, and other tests call gpt-3.5-turbo with
custom temperature / logprobs / the legacy /v1/completions endpoint.
The earlier modernization mapped both aliases to gpt-5.5 / gpt-5-mini,
which are reasoning models that reject temperature != 1 and don't
expose /v1/completions. Map the aliases to gpt-4.1 / gpt-4.1-mini
(modern non-reasoning OpenAI models) instead — keeps user-facing
aliases preserved while picking a current underlying that still
supports the parameters/endpoints the tests exercise.
AWS Bedrock has reached end-of-life for `claude-3-7-sonnet-20250219-v1:0`,
returning 404s with "This model version has reached the end of its life."
Update test references to `claude-sonnet-4-5-20250929-v1:0` (same capability
surface: thinking, tools, prompt caching, PDF input, vision, computer use).
The bedrock/invoke pass-through tests stay on Sonnet 3.5 since Sonnet 4.5
is converse-only on Bedrock.
Cost tracking was failing for Responses API when using custom deployment names
with base_model configuration. The issue occurred because:
- Chat Completions API stores model_info in 'metadata'
- Responses API stores model_info in 'litellm_metadata'
- Cost calculator only checked 'metadata', missing Responses API costs
Changes:
- Updated _get_base_model_from_metadata() to check both metadata locations
- Added comprehensive unit tests covering all scenarios
- Maintains backward compatibility (metadata takes precedence)
Fixes#16772
- Test multiple tool calls without explicit indices receive sequential indices
- Verify Delta class assigns indices 0, 1, 2... instead of defaulting all to 0
- Add comprehensive assertions for tool call details preservation
- Cover provider-agnostic streaming response scenarios
* Check content and order of trimmed messages
* Assert tool calls are preserved if below max_tokens
* Unreverse order of tool calls
* Return tool calls alongside other messages
* Write test for trimming untokenizable field
* Return original messages in case of exception
* fix: add flag for disabling use_aiohttp_transport
* feat: add _create_async_transport
* feat: fixes for transport
* add httpx-aiohttp
* feat: fixes for transport
* refactor: fixes for transport
* build: fix deps
* fixes: test fixes
* fix: ensure aiohttp does not auto set content type
* test: test fixes
* feat: add LiteLLMAiohttpTransport
* fix: fixes for responses API handling
* test: fixes for responses API handling
* test: fixes for responses API handling
* feat: fixes for transport
* fix: base embedding handler
* test: test_async_http_handler_force_ipv4
* test: fix failing deepeval test
* fix: add YARL for bedrock urls
* fix: issues with transport
* fix: comment out linting issues
* test fix
* test: XAI is unstable
* test: fixes for using respx
* test: XAI fixes
* test: XAI fixes
* test: infinity testing fixes
* docs(config_settings.md): document param
* test: test_openai_image_edit_litellm_sdk
* test: remove deprecated test
* bump respx==0.22.0
* test: test_xai_message_name_filtering
* test: fix anthropic test after bumping httpx
* use n 4 for mapped tests (#11109)
* fix: use 1 session per event loop
* test: test_client_session_helper
* fix: linting error
* fix: resolving GET requests on httpx 0.28.1
* test fixes proxy unit tests
* fix: add ssl verify settings
* fix: proxy unit tests
* fix: refactor
* tests: basic unit tests for aiohttp transports
* tests: fixes xai
---------
Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
* added tests
messages_with_counts: Made tolerance explicit for each test. But they match the new implementation(which beats the old)
* new token counter impl
* compare old and new implementation in test
* delete old token counter
* moved tests to /tests/litellm/litellm_core_utils
* use existing types
* docstrings
* warn about using default params on unknown model.
* created type for the token_counter_function
* check key == "content"
* throw error on invalid detail-type, ignore type-warning.
* fix imports
* feat(utils.py): support global flag for 'check_provider_endpoints'
enables setting this for `/models` on proxy
* feat(utils.py): add caching to 'get_valid_models'
Prevents checking endpoint repeatedly
* fix(utils.py): ensure mutations don't impact cached results
* test(test_utils.py): add unit test to confirm cache invalidation logic
* feat(utils.py): get_valid_models - support passing litellm params dynamically
Allows for checking endpoints based on received credentials
* test: update test
* feat(model_checks.py): pass router credentials to get_valid_models - ensures it checks correct credentials
* refactor(utils.py): refactor for simpler functions
* fix: fix linting errors
* fix(utils.py): fix test
* fix(utils.py): set valid providers to custom_llm_provider, if given
* test: update test
* fix: fix ruff check error
* fix: initial commit for adding provider model discovery to gemini
* feat(gemini/): add model discovery for gemini/ route
* docs(set_keys.md): update docs to show you can check available gemini models as well
* feat(anthropic/): add model discovery for anthropic api key
* feat(xai/): add model discovery for XAI
enables checking what models an xai key can call
* ci: bump ci config yml
* fix(topaz/common_utils.py): fix linting error
* fix: fix linting error for python38
* refactor: introduce new transformation config for gpt-4o-transcribe models
* refactor: expose new transformation configs for audio transcription
* ci: fix config yml
* feat(openai/transcriptions): support provider config transformation on openai audio transcriptions
allows gpt-4o and whisper audio transformation to work as expected
* refactor: migrate fireworks ai + deepgram to new transform request pattern
* feat(openai/): working support for gpt-4o-audio-transcribe
* build(model_prices_and_context_window.json): add gpt-4o-transcribe to model cost map
* build(model_prices_and_context_window.json): specify what endpoints are supported for `/audio/transcriptions`
* fix(get_supported_openai_params.py): fix return
* refactor(deepgram/): migrate unit test to deepgram handler
* refactor: cleanup unused imports
* fix(get_supported_openai_params.py): fix linting error
* test: update test
* feat(bedrock/converse/transformation.py): support claude-3-7-sonnet reasoning_Content transformation
Closes https://github.com/BerriAI/litellm/issues/8777
* fix(bedrock/): support returning `reasoning_content` on streaming for claude-3-7
Resolves https://github.com/BerriAI/litellm/issues/8777
* feat(bedrock/): unify converse reasoning content blocks for consistency across anthropic and bedrock
* fix(anthropic/chat/transformation.py): handle deepseek-style 'reasoning_content' extraction within transformation.py
simpler logic
* feat(bedrock/): fix streaming to return blocks in consistent format
* fix: fix linting error
* test: fix test
* feat(factory.py): fix bedrock thinking block translation on tool calling
allows passing the thinking blocks back to bedrock for tool calling
* fix(types/utils.py): don't exclude provider_specific_fields on model dump
ensures consistent responses
* fix: fix linting errors
* fix(convert_dict_to_response.py): pass reasoning_content on root
* fix: test
* fix(streaming_handler.py): add helper util for setting model id
* fix(streaming_handler.py): fix setting model id on model response stream chunk
* fix(streaming_handler.py): fix linting error
* fix(streaming_handler.py): fix linting error
* fix(types/utils.py): add provider_specific_fields to model stream response
* fix(streaming_handler.py): copy provider specific fields and add them to the root of the streaming response
* fix(streaming_handler.py): fix check
* fix: fix test
* fix(types/utils.py): ensure messages content is always openai compatible
* fix(types/utils.py): fix delta object to always be openai compatible
only introduce new params if variable exists
* test: fix bedrock nova tests
* test: skip flaky test
* test: skip flaky test in ci/cd
* feat(litellm_pre_call_utils.py): support `x-litellm-tags` request header
allow tag based routing + spend tracking via request headers
* docs(request_headers.md): document new `x-litellm-tags` for tag based routing and spend tracking
* docs(tag_routing.md): add to docs
* fix(utils.py): only pass str values for openai metadata param
* fix(utils.py): drop non-str values for metadata param to openai
preview-feature, otel span was being sent in
* use class ResetBudgetJob
* refactor reset budget job
* update reset_budget job
* refactor reset budget job
* fix LiteLLM_UserTable
* refactor reset budget job
* add telemetry for reset budget job
* dd - log service success/failure on DD
* add detailed reset budget reset info on DD
* initialize_scheduled_background_jobs
* refactor reset budget job
* trigger service failure hook when fails to reset a budget for team, key, user
* fix resetBudgetJob
* unit testing for ResetBudgetJob
* test_duration_in_seconds_basic
* testing for triggering service logging
* fix logs on test teams fail
* remove unused imports
* fix import duration in s
* duration_in_seconds
Mateo Wang