scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(arize): _set_usage_outputs handles raw OpenAI Pydantic CompletionUsage (#26506)

Browse source 
* [Feat] Day-0 support for GPT-5.5 and GPT-5.5 Pro (#26449)

* feat(openai): day-0 support for GPT-5.5 and GPT-5.5 Pro

Add pricing + capability entries for the new GPT-5.5 family launched by
OpenAI on 2026-04-24:

- gpt-5.5 / gpt-5.5-2026-04-23 (chat): $5/$30/$0.50 per 1M
  input/output/cached input
- gpt-5.5-pro / gpt-5.5-pro-2026-04-23 (responses-only): $60/$360/$6
  per 1M input/output/cached input

Other fees (long-context >272k, flex, batches, priority, cache
discounts) follow the same ratios as GPT-5.4, with context window
retained at 1.05M input / 128K output.

No transformation / classifier code changes are required:
OpenAIGPT5Config.is_model_gpt_5_4_plus_model() already matches 5.5+ via
numeric version parsing, and model registration is driven from the
JSON. The existing responses-API bridge for tools + reasoning_effort
(litellm/main.py:970) already covers gpt-5.5-pro.

Tests:
- GPT5_MODELS regression list now covers gpt-5.5-pro and dated variants
- New test_generic_cost_per_token_gpt55_pro cost-calc test
- Updated test_generic_cost_per_token_gpt55 for long-context fields

* fix(openai): mirror reasoning_effort flags onto gpt-5.5 dated variants

gpt-5.5-2026-04-23 and gpt-5.5-pro-2026-04-23 were missing the
supports_none_reasoning_effort, supports_xhigh_reasoning_effort, and
supports_minimal_reasoning_effort flags that their non-dated
counterparts define. Reasoning-effort routing in OpenAIGPT5Config is
fully capability-driven from these JSON flags — since an absent flag
is treated as False for opt-in levels (xhigh), users pinning to a
dated snapshot would silently lose xhigh support and diverge from the
base alias on logprobs + flexible temperature handling.

Copy the flags onto both dated variants so every dated snapshot
inherits the base model's reasoning-effort capability profile.

Adds a parametrized regression test that asserts
supports_{none,minimal,xhigh}_reasoning_effort parity between each
dated variant and its non-dated counterpart, preventing future drift
when new snapshots are added.

* [Feat] Add azure/gpt-5.5 + azure/gpt-5.5-pro entries (+ dated variants) (#26361)

* feat(azure): add azure/gpt-5.5 + azure/gpt-5.5-pro entries (+ dated variants)

Azure variants of OpenAI's GPT-5.5 family. Microsoft has not yet
shipped GPT-5.5 on Azure OpenAI (latest GA on the Foundry models page
is GPT-5.4 as of 2026-04-24), but adding the entries day-0 mirrors the
established precedent for azure/gpt-5.4* (which were in the cost map
before the Azure rollout) so cost tracking and capability flags work
the moment customers deploy.

Schema follows the existing azure/gpt-5.4* shape:
- Same base/long-context pricing as openai/gpt-5.5*: $5/$30 chat,
  $60/$360 pro per 1M, with priority tier 2x base
- Azure variants drop the flex/batches keys (Azure has no flex tier)
  but keep priority pricing, matching gpt-5.4* precedent
- mode=chat for the thinking model, mode=responses for pro

reasoning_effort capability flags mirror the OpenAI variants exactly
since Azure proxies the same API contract: minimal rejection on both
chat and pro, low/none rejection on pro. Once #26456 (which sets
supports_low_reasoning_effort + minimal=false on openai/gpt-5.5*)
lands, OpenAI and Azure flag profiles align.

Tests pin entry presence + pricing for all four Azure variants and
verify the live-API-derived reasoning_effort flags.

* test: register supports_low_reasoning_effort in cost-map JSON schema

azure/gpt-5.5-pro and azure/gpt-5.5-pro-2026-04-23 added in this branch
carry supports_low_reasoning_effort=false. The strict
'additionalProperties: false' schema in
test_aaamodel_prices_and_context_window_json_is_valid rejected the new
key. Register it alongside the other supports_*_reasoning_effort
entries.

Note: the runtime side of this flag (code that reads it) lands in
#26456. Until that PR merges the flag is inert for both Azure and
OpenAI pro entries, but having the schema accept it lets cost-map
tests pass on either merge order.

* fix(arize/langfuse_otel): handle Pydantic usage objects without `.get`

`_set_usage_outputs` called `usage.get(...)` and
`usage.get('output_tokens_details', {}).get('reasoning_tokens')`. These
crash with `AttributeError: 'CompletionUsage' object has no attribute
'get'` when `usage` (or the nested token-details object) is a raw OpenAI
Pydantic model rather than a dict / litellm `Usage` wrapper. Reproduces
on the langfuse_otel + arize Responses API logging paths.

Fixes #13672.

Changes:
- Add `_safe_get(obj, key, default)` that prefers dict-style `.get` when
  available and otherwise falls back to `getattr`. Works uniformly for
  dicts, litellm's `Usage`, and plain Pydantic models like
  `openai.types.completion_usage.CompletionUsage` /
  `CompletionTokensDetails` / `OutputTokensDetails`.
- Use `_safe_get` for total / completion / prompt / output tokens.
- Look for reasoning tokens in `completion_tokens_details` (Chat
  Completions API) before falling back to `output_tokens_details`
  (Responses API). Previously reasoning tokens from the Chat Completions
  API were silently dropped.

Tests:
- `test_set_usage_outputs_pydantic_completion_usage` — covers the chat
  completions path with raw `CompletionUsage` + `CompletionTokensDetails`.
- `test_set_usage_outputs_pydantic_response_api_usage` — covers the
  Responses API path with a Pydantic usage object lacking `.get`.

Both tests fail on main before this commit and pass after.

---------

Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: alvinttang <alvin@pm.me>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
This commit is contained in:
Alvin Tang 2026-04-26 05:11:51 +08:00 • committed by GitHub
parent f63a6f1b26
commit 98a9005c76
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 450 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
litellm/integrations/arize/_utils.py
View file

@ -220,23 +220,57 @@ def _set_structured_outputs(span: "Span", response_obj, msg_attrs, span_attrs):
safe_set_attribute(span, f"{prefix}.{msg_attrs.MESSAGE_ROLE}", message_role)
def _safe_get(obj, key, default=None):
"""Read ``key`` from a dict-like or Pydantic-model-like object.
The arize/langfuse_otel logger receives ``usage`` objects from many sources:
plain dicts, litellm ``Usage`` (which exposes ``.get``), and raw OpenAI
Pydantic models (e.g. ``openai.types.completion_usage.CompletionUsage`` and
nested ``CompletionTokensDetails`` / ``OutputTokensDetails``) which do NOT
expose ``.get``. Calling ``.get`` on the latter raised ``AttributeError`` —
see https://github.com/BerriAI/litellm/issues/13672.
"""
if obj is None:
return default
getter = getattr(obj, "get", None)
if callable(getter):
try:
return getter(key, default)
except TypeError:
# Some objects expose `.get` with a different signature
pass
return getattr(obj, key, default)
def _set_usage_outputs(span: "Span", response_obj, span_attrs):
usage = response_obj and response_obj.get("usage")
if not usage:
return
safe_set_attribute(
span, span_attrs.LLM_TOKEN_COUNT_TOTAL, usage.get("total_tokens")
span, span_attrs.LLM_TOKEN_COUNT_TOTAL, _safe_get(usage, "total_tokens")
)
completion_tokens = _safe_get(usage, "completion_tokens") or _safe_get(
usage, "output_tokens"
)
completion_tokens = usage.get("completion_tokens") or usage.get("output_tokens")
if completion_tokens:
safe_set_attribute(
span, span_attrs.LLM_TOKEN_COUNT_COMPLETION, completion_tokens
)
prompt_tokens = usage.get("prompt_tokens") or usage.get("input_tokens")
prompt_tokens = _safe_get(usage, "prompt_tokens") or _safe_get(
usage, "input_tokens"
)
if prompt_tokens:
safe_set_attribute(span, span_attrs.LLM_TOKEN_COUNT_PROMPT, prompt_tokens)
reasoning_tokens = usage.get("output_tokens_details", {}).get("reasoning_tokens")
# Reasoning tokens live in `completion_tokens_details` for Chat Completions
# API (Usage) and in `output_tokens_details` for Responses API
# (ResponseAPIUsage). Both nested objects may be plain Pydantic models
# without `.get`.
token_details = _safe_get(usage, "completion_tokens_details") or _safe_get(
usage, "output_tokens_details"
)
reasoning_tokens = _safe_get(token_details, "reasoning_tokens")
if reasoning_tokens:
safe_set_attribute(
span,

163
litellm/model_prices_and_context_window_backup.json
View file

@ -4645,6 +4645,169 @@
"supports_vision": true,
"supports_web_search": true
},
"azure/gpt-5.5": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/gpt-5.5-pro": {
"cache_read_input_token_cost": 6e-06,
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
"input_cost_per_token": 6e-05,
"input_cost_per_token_above_272k_tokens": 0.00012,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00036,
"output_cost_per_token_above_272k_tokens": 0.00054,
"supported_endpoints": [
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_low_reasoning_effort": false
},
"azure/gpt-5.5-pro-2026-04-23": {
"cache_read_input_token_cost": 6e-06,
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
"input_cost_per_token": 6e-05,
"input_cost_per_token_above_272k_tokens": 0.00012,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00036,
"output_cost_per_token_above_272k_tokens": 0.00054,
"supported_endpoints": [
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 7.5e-07,

163
model_prices_and_context_window.json
View file

@ -4659,6 +4659,169 @@
"supports_vision": true,
"supports_web_search": true
},
"azure/gpt-5.5": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/gpt-5.5-pro": {
"cache_read_input_token_cost": 6e-06,
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
"input_cost_per_token": 6e-05,
"input_cost_per_token_above_272k_tokens": 0.00012,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00036,
"output_cost_per_token_above_272k_tokens": 0.00054,
"supported_endpoints": [
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_low_reasoning_effort": false
},
"azure/gpt-5.5-pro-2026-04-23": {
"cache_read_input_token_cost": 6e-06,
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
"input_cost_per_token": 6e-05,
"input_cost_per_token_above_272k_tokens": 0.00012,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00036,
"output_cost_per_token_above_272k_tokens": 0.00054,
"supported_endpoints": [
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 7.5e-07,

85
tests/test_litellm/integrations/arize/test_arize_utils.py
View file

@ -273,6 +273,91 @@ def test_arize_set_attributes_responses_api():
)
def test_set_usage_outputs_pydantic_completion_usage():
"""
Regression test for https://github.com/BerriAI/litellm/issues/13672
`_set_usage_outputs` previously called `usage.get(...)` which crashes when
`usage` is a plain Pydantic model (e.g. openai.types.completion_usage.CompletionUsage)
that does not implement dict-style `.get()`. Same crash for nested
`output_tokens_details` / `completion_tokens_details`.
The function must:
1. Read total/prompt/completion tokens from a Pydantic usage without `.get`.
2. Read reasoning_tokens from `completion_tokens_details` (chat completions API)
OR `output_tokens_details` (responses API), even when those nested objects
are Pydantic models without `.get`.
3. Not raise AttributeError; not call span.record_exception.
"""
from unittest.mock import MagicMock
from openai.types.completion_usage import (
CompletionTokensDetails,
CompletionUsage,
)
from litellm.integrations.arize._utils import _set_usage_outputs
span = MagicMock()
# Plain OpenAI Pydantic model — has no `.get()`
usage = CompletionUsage(
completion_tokens=60,
prompt_tokens=40,
total_tokens=100,
completion_tokens_details=CompletionTokensDetails(reasoning_tokens=25),
)
assert not hasattr(usage, "get"), "precondition: CompletionUsage must lack .get"
response_obj = {"usage": usage}
# Must not raise
_set_usage_outputs(span, response_obj, SpanAttributes)
span.set_attribute.assert_any_call(SpanAttributes.LLM_TOKEN_COUNT_TOTAL, 100)
span.set_attribute.assert_any_call(SpanAttributes.LLM_TOKEN_COUNT_PROMPT, 40)
span.set_attribute.assert_any_call(SpanAttributes.LLM_TOKEN_COUNT_COMPLETION, 60)
# reasoning_tokens for chat completions live in completion_tokens_details
span.set_attribute.assert_any_call(
SpanAttributes.LLM_TOKEN_COUNT_COMPLETION_DETAILS_REASONING, 25
)
def test_set_usage_outputs_pydantic_response_api_usage():
"""
Same crash also affects Responses API with `output_tokens_details` as a
Pydantic model that lacks `.get()`. Verifies the responses-API path.
"""
from unittest.mock import MagicMock
from litellm.integrations.arize._utils import _set_usage_outputs
from litellm.types.llms.openai import OutputTokensDetails
# Build an object that mimics openai ResponsesAPI usage but lacks `.get`
# (uses a plain class — not BaseLiteLLMOpenAIResponseObject)
class PlainResponsesUsage:
def __init__(self):
self.total_tokens = 370
self.input_tokens = 120
self.output_tokens = 250
self.output_tokens_details = OutputTokensDetails(reasoning_tokens=180)
usage = PlainResponsesUsage()
assert not hasattr(usage, "get")
span = MagicMock()
response_obj = {"usage": usage}
_set_usage_outputs(span, response_obj, SpanAttributes)
span.set_attribute.assert_any_call(SpanAttributes.LLM_TOKEN_COUNT_TOTAL, 370)
span.set_attribute.assert_any_call(SpanAttributes.LLM_TOKEN_COUNT_PROMPT, 120)
span.set_attribute.assert_any_call(SpanAttributes.LLM_TOKEN_COUNT_COMPLETION, 250)
span.set_attribute.assert_any_call(
SpanAttributes.LLM_TOKEN_COUNT_COMPLETION_DETAILS_REASONING, 180
)
class TestArizeLogger(CustomLogger):
"""
Custom logger implementation to capture standard_callback_dynamic_params.

1
tests/test_litellm/test_utils.py
View file

@ -769,6 +769,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"uses_embed_content": {"type": "boolean"},
"supports_reasoning": {"type": "boolean"},
"supports_minimal_reasoning_effort": {"type": "boolean"},
"supports_low_reasoning_effort": {"type": "boolean"},
"supports_none_reasoning_effort": {"type": "boolean"},
"supports_xhigh_reasoning_effort": {"type": "boolean"},
"supports_max_reasoning_effort": {"type": "boolean"},