Chesars
a0cfb56801
fix(pricing): correct audio token costs for gpt-4o-audio-preview models
...
Update audio token pricing for gpt-4o-audio-preview and
gpt-4o-audio-preview-2024-10-01 to match OpenAI's official pricing:
- input_cost_per_audio_token: 0.0001 -> 4e-05 ($40/1M tokens)
- output_cost_per_audio_token: 0.0002 -> 8e-05 ($80/1M tokens)
The previous values were 2.5x higher than OpenAI's actual pricing.
2026-01-21 10:46:03 -03:00
Sameer Kankute
e758dd0a59
Merge pull request #19472 from BerriAI/litellm_fix_chat_completion_responses_streaming
...
Fix: tool call streaming in chat completion bridge
2026-01-21 19:15:53 +05:30
Sameer Kankute
34d4c5d3fc
Fix mypy litellm_timeout_fix
2026-01-21 19:12:44 +05:30
Sameer Kankute
540370a1aa
Merge pull request #19479 from BerriAI/litellm_sarvam_int
...
Add support for sarvam models
2026-01-21 19:03:52 +05:30
Sameer Kankute
cc92ca088d
remove print statements
2026-01-21 19:00:01 +05:30
Sameer Kankute
c26c06d5b5
remove print statements
2026-01-21 18:59:51 +05:30
Sameer Kankute
b6691baf24
Merge pull request #19482 from BerriAI/litellm_anthropic_max_length
...
Filter out unsupported fields from JSON schema for Anthropic's output_format API.
2026-01-21 18:57:16 +05:30
Sameer Kankute
751786aab9
fix ./tests/code_coverage_tests/check_provider_folders_documented.py
2026-01-21 18:54:32 +05:30
Sameer Kankute
e315e4cd7c
fix litellm/tests/litellm_utils_tests/test_utils.py
2026-01-21 18:50:02 +05:30
Sameer Kankute
b374b2f605
Fix mypy issues in streaming iterator
2026-01-21 18:45:15 +05:30
Sameer Kankute
aeb38ffa9b
Merge pull request #19497 from BerriAI/main
...
merge main
2026-01-21 18:43:27 +05:30
Sameer Kankute
d145a36c90
Fix: mypy chat transformation
2026-01-21 18:35:51 +05:30
Sameer Kankute
ba36981bed
Merge pull request #19486 from BerriAI/litellm_fix_serialisation_problem
...
Fix: [Bug]: litellm.litellm_core_utils.litellm_logging.Logging incorrectly handles ResponseAPIResponse
2026-01-21 18:32:30 +05:30
Sameer Kankute
b0499841b0
Merge pull request #19461 from BerriAI/litellm_staging_01_20_2026
...
Litellm staging 01 20 2026
2026-01-21 18:31:14 +05:30
Sameer Kankute
491eaaa0e0
Merge pull request #19495 from BerriAI/litellm_staging_01_20_2026_fixes
...
Litellm staging 01 20 2026 fixes
2026-01-21 17:40:58 +05:30
Sameer Kankute
22158f8f03
Fix litellm_staging_01_20_2026 mypy issues
2026-01-21 17:35:28 +05:30
Sameer Kankute
c8d065656e
Fix litellm_staging_01_20_2026 mypy issues
2026-01-21 17:33:53 +05:30
Sameer Kankute
6e1ecabd9a
Merge pull request #19493 from BerriAI/revert-19391-fix/prisma-schema-permission
...
Revert "Fix/prisma schema permission"
2026-01-21 17:19:43 +05:30
Sameer Kankute
d879dcdcef
Revert "Fix/prisma schema permission ( #19391 )"
...
This reverts commit 75ee0d126c
2026-01-21 17:19:32 +05:30
Sameer Kankute
37d27e67d5
Merge pull request #19489 from cluebbehusen/fix-gemini-2-5-flash-lite-pricing
...
fix: correct gemini-2.5-flash-lite audio input and cache read pricing
2026-01-21 16:41:22 +05:30
Sameer Kankute
a1aba2ed8d
Merge pull request #19491 from BerriAI/main
...
merge main 20 1 25
2026-01-21 16:40:48 +05:30
Connor Luebbehusen
b810a68f89
fix: correct gemini-2.5-flash-lite audio input and cache read pricing
2026-01-21 05:58:38 -05:00
Sameer Kankute
3748c70675
Fix: [Bug]: litellm.litellm_core_utils.litellm_logging.Logging incorrectly handles ResponseAPIResponse
2026-01-21 16:15:54 +05:30
Sameer Kankute
c571a02f3b
Filter out unsupported fields from JSON schema for Anthropic's output_format API.
2026-01-21 15:48:22 +05:30
Sameer Kankute
46c0f903a3
Add support for sarvam models
2026-01-21 15:17:26 +05:30
Sameer Kankute
4127654807
Add REASONING_SUMMARY_TEXT_DONE and REASONING_SUMMARY_PART_DONE events in streaming
2026-01-21 14:32:05 +05:30
Sameer Kankute
828ff1c99e
Added output item for chunk based on type
2026-01-21 13:25:44 +05:30
Sameer Kankute
3a0d166eb0
Fix: tool call streaming in chat completino brigde
2026-01-21 12:14:02 +05:30
Yuta Saito
a312ef31e3
chore: fix mypy
2026-01-21 15:04:24 +09:00
Yuta Saito
165081059a
chore: ruff fix
2026-01-21 14:57:14 +09:00
Yuta Saito
72cbc295e5
chore: format
2026-01-21 14:54:50 +09:00
Yuta Saito
caf5f7f8ae
test: add test
2026-01-21 14:51:56 +09:00
yuneng-jiang
032b1a8cd2
Fixing tests
2026-01-20 21:51:13 -08:00
yuneng-jiang
4b9baade48
Adding tests
2026-01-20 21:50:28 -08:00
yuneng-jiang
90bd80a4c2
fixing build
2026-01-20 21:46:21 -08:00
yuneng-jiang
2441b05700
Fix MCP Server resetting back to Overview
2026-01-20 21:38:58 -08:00
Yuta Saito
872e5b9897
feat: log mcp list_tools calls to SpendLogs
2026-01-21 14:32:08 +09:00
Yuta Saito
ae4d92ad50
feat: save mcp call log via responses
2026-01-21 13:54:24 +09:00
Ishaan Jaff
a02c43d300
Litellm cc docs max ( #19466 )
...
* docs claude code max
* docs fix
* docs
* docs fix
* docs fix
2026-01-20 20:08:36 -08:00
Sameer Kankute
a5ea08a0bf
Fix test_default_api_base failing because of chatgpt as provider
2026-01-21 09:32:38 +05:30
Ryne Carbone
15013cec4b
feat(gemini): add file content support in tool results ( #19416 )
...
Add support for 'file' and 'input_file' content types in
convert_to_gemini_tool_call_result(). File content in tool
results was previously silently dropped.
Supports base64 data URIs and HTTP URLs, matching the existing
image handling pattern. Enables PDF, audio, video, and other
file types as inline_data for Gemini.
2026-01-20 19:54:12 -08:00
Sameer Kankute
a5b8da7f87
Merge pull request #19463 from BerriAI/litellm_2101_cicd_fixes
...
Fixes test_aaabasic_gcs_logger
2026-01-21 09:22:40 +05:30
Cesar Garcia
12c6dde1c3
fix(ui): increase model selector width in playground for larger screens ( #19423 )
...
Make the model/agent selector responsive with wider widths on tablet (256px) and desktop (288px) for better usability.
2026-01-20 19:47:52 -08:00
Lucky-Lodhi2004
efbdf9d60d
fix #19414 - [Bug]: get_model_info on Bedrock suffixed models doesn't return proper information ( #19421 )
...
* fixed get_model_info for bedrock models
* fixed import
2026-01-20 19:45:55 -08:00
Cesar Garcia
b4ed387d24
fix(vertex_ai): handle reasoning_effort as dict from OpenAI Agents SDK ( #19419 )
...
The OpenAI Agents SDK (v0.6.9+) now passes reasoning_effort as a dict
when summary is specified: {"effort": "high", "summary": "auto"}
This change extracts the "effort" value from the dict for Vertex AI,
which only supports thinkingLevel (not summary).
Before: reasoning_effort={"effort": "high"} was silently ignored
After: reasoning_effort={"effort": "high"} correctly maps to thinkingLevel
Fixes #19411
2026-01-20 19:31:25 -08:00
Sameer Kankute
0b9f6b543f
Fixes test_aaabasic_gcs_logger
2026-01-21 08:58:16 +05:30
Harshit Jain
76433f9f04
fix: add better error handling for misconfig on health check ( #19441 )
2026-01-20 19:24:28 -08:00
Sampson
09941dd1d1
add search provider for brave search api ( #19433 )
...
* add search provider for brave search api
Introduces a minimal implementation of the Brave Search API as a search provider. Additionally, this PR introduces a test file to ensure the provider works properly, and numerous other smaller changes (e.g., changes to docs to mention the new option).
* Update transformation.py
2026-01-20 19:23:29 -08:00
Kamil Jopek
ce722ab763
Make grpc dependency optional ( #19447 )
...
* Make grpc optional and document gRPC OTEL setup
* Add tests for missing OTLP gRPC imports
2026-01-20 19:03:52 -08:00
Harshit Jain
3c3148789a
fix: resolve Read-only file system error in non-root images ( #19449 )
2026-01-20 19:00:52 -08:00
