Commit graph

32324 commits

Author SHA1 Message Date
yuneng-jiang
b5a7d2ab34 Paginating model/info endpoint 2026-01-21 10:44:18 -08:00
John Greek
aa4b0e0149
Fix duplicate test_handler.py filenames causing pytest collection errors (#19385) 2026-01-21 08:47:50 -08:00
Chesars
796e93552d Fix gpt-audio models pricing and add dated snapshots
- Fix audio token pricing for gpt-audio ($32/$64 per 1M, not $40/$80)
- Add gpt-audio-2025-08-28 snapshot (OpenAI returns this in responses)
- Add gpt-audio-mini-2025-10-06 and gpt-audio-mini-2025-12-15 snapshots
- Add missing fields: supported_endpoints, supported_modalities,
  supported_output_modalities, supports_native_streaming, etc.
2026-01-21 13:05:38 -03:00
Chesars
da8770004c Add gpt-audio and gpt-audio-mini models to pricing
Fixes #19490 - adds missing OpenAI audio models with correct pricing:

gpt-audio:
- Text: $2.50/$10.00 per 1M tokens (input/output)
- Audio: $40/$80 per 1M tokens (input/output)

gpt-audio-mini:
- Text: $0.60/$2.40 per 1M tokens (input/output)
- Audio: $10/$20 per 1M tokens (input/output)
2026-01-21 12:47:10 -03:00
Chesars
f64ff8327d docs(custom_pricing): add base_model usage for OpenAI dated model versions
Document how to use base_model to ensure custom pricing is applied when
OpenAI returns dated model names (e.g., gpt-4o-mini-audio-preview-2024-12-17)
that differ from the configured model name.
2026-01-21 11:18:51 -03:00
Sameer Kankute
95dc14e400
Merge pull request #19389 from BerriAI/litellm_timeout_fix
Fix: total timeout is not respected
2026-01-21 19:16:11 +05:30
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