Sameer Kankute d8f139fe4d feat(openai): add 272K tier pricing for GPT-5.4/5.4-pro ...

Prompts >272K input tokens priced at 2x input, 1.5x output for full session
(standard, batch, flex). Applies to models with 1.05M context window (gpt-5.4,
gpt-5.4-pro).

- Add input/output_cost_per_token_above_272k_tokens to model_prices
- Add above_272k fields to ModelInfoBase and get_model_info extraction
- Add test_generic_cost_per_token_gpt54_above_272k_tokens

Made-with: Cursor

2026-03-06 22:26:14 +05:30

..

llm_cost_calc

feat(openai): add 272K tier pricing for GPT-5.4/5.4-pro

2026-03-06 22:26:14 +05:30

llm_response_utils

fix: reduce proxy overhead for large base64 payloads (#21594)

2026-02-19 12:10:52 -08:00

prompt_templates

Agent Builder - support new experimental agent builder, to ensure agents pass compliance checks (#21817)

2026-02-21 15:32:47 -08:00

specialty_caches

[Performance] Reduce complexity of InMemoryCache.evict_cache from O(n*log(n)) to O(log(n)) (#15000)

2025-09-30 16:49:35 -07:00

__init__.py

…

messages_with_counts.py

…

test_audio_utils.py

Use audio content for caching

2025-12-08 19:31:22 +05:30

test_cli_token_utils.py

…

test_codestral_provider_routing.py

fix: correctly route codestral chat and FIM endpoints (#18467)

2026-01-04 00:45:45 +05:30

test_core_helpers.py

fix: unify model names to provider-defined names

2026-01-02 08:36:58 +09:00

test_coroutine_checker.py

…

test_dd_tracing.py

…

test_dot_notation_indexing.py

Add Kubernetes ServiceAccount JWT authentication support (#18055)

2026-01-02 14:02:31 +05:30

test_duration_parser.py

fix(budget): fix timezone config lookup and replace hardcoded timezone map with ZoneInfo (#21754)

2026-02-21 19:35:06 -08:00

test_exception_mapping_utils.py

fix openai tests

2026-02-12 17:53:47 -08:00

test_extract_base64_image.py

fix: extract pure base64 data from data URLs for Ollama (#18465)

2026-01-04 00:47:38 +05:30

test_get_litellm_params.py

Fix credential name tag injection by moving to Router level

2026-02-20 17:16:36 -08:00

test_health_check_helpers.py

Fix: Prevent LiteLLM API key leakage on /health endpoint failures (#18133)

2025-12-17 08:08:05 -08:00

test_image_handling.py

Fix: Stream the download in chunks

2026-01-27 14:35:54 +05:30

test_litellm_logging.py

test_get_usage_as_dict

2026-02-21 15:39:06 -08:00

test_logging_utils.py

fix: reduce proxy overhead for large base64 payloads (#21594)

2026-02-19 12:10:52 -08:00

test_logging_worker.py

fix(logging_worker): handle event loop changes in multiprocessing by checking bound_loop (#18423)

2026-01-03 00:19:14 +05:30

test_max_streaming_duration.py

[Feat] Add control for setting upperbound on chunk processing time (#22209)

2026-02-26 11:39:09 -08:00

test_model_response_utils.py

…

test_provider_specific_headers.py

[Fix] Forward anthropic-beta headers to Bedrock, VertexAI (#15700)

2025-10-18 16:26:32 -07:00

test_realtime_streaming.py

fix: update stale docstring to match guardrail voicing behavior

2026-02-27 23:04:43 -03:00

test_redact_messages.py

fix: redaction headers ignored when sent via proxy (#20740)

2026-02-11 15:44:37 +05:30

test_retry_after_headers.py

Add retry-after header support for errors 502, 503, 504 (#16288)

2025-11-06 19:33:29 -08:00

test_safe_divide_seconds.py

…

test_safe_json_dumps.py

fix: shared health check serialization (#21119)

2026-02-13 09:15:43 -08:00

test_sensitive_data_masker.py

fix: don't mask cost_per_token fields in SensitiveDataMasker

2026-02-20 18:13:27 -08:00

test_streaming_chunk_builder_utils.py

fix(responses): eliminate per-chunk thread spawning in async streaming path (#21709)

2026-02-20 16:26:23 -08:00

test_streaming_handler.py

fix(streaming): prevent Vertex AI Claude content truncation when finish_reason races content

2026-03-04 22:44:48 +01:00

test_token_counter_tool_data.py

…

test_token_counter_tool.py

…

test_token_counter.py

fix(token-counter): fix test isolation and encode() return type normalization

2026-02-17 20:07:52 -03:00