tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-16 16:17:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
30,058 Commits 2,072 Branches 1,425 Tags
ebeea46fc4e12ac9ee79acbf19bc8a8585322e9f
Commit Graph
1185 Commits
Author SHA1 Message Date
Sameer KankuteandGitHub 9a27a52424 Merge pull request #18956 from BerriAI/litellm_staging_01_12_2026 
Litellm staging 01 12 2026
 2026-01-12 18:27:57 +05:30
Sameer KankuteandGitHub ebf61998e0 Merge pull request #18954 from BerriAI/litellm_replicate_support 
[Feat] Add all chat replicate models support
 2026-01-12 18:15:46 +05:30
Cesar GarciaGitHubThomas Rehn
 		932f06104d fix: include IMAGE token count in cost calculation for Gemini models (#18876) 
* fix: include IMAGE token count as separate usage count and pricing

* fix: remove duplicate TypedDict key and variable definitions

- Remove duplicate input_cost_per_image_token in ModelInfoBase TypedDict
- Remove duplicate image_tokens variable declaration in _calculate_usage()

Fixes MyPy errors:
- types/utils.py:146: Duplicate TypedDict key
- vertex_and_google_ai_studio_gemini.py:1541: Name already defined

---------

Co-authored-by: Thomas Rehn <271119+tremlin@users.noreply.github.com>
 2026-01-12 17:03:42 +05:30
Sameer Kankute 3d38ec4756 Add all replicate models in model cost map 2026-01-12 15:19:49 +05:30
Sameer KankuteandGitHub 7e3760b740 Merge pull request #18899 from Chesars/claude/check-gpt-oss-pricing-4wKrq 
fix: correct pricing for openrouter/openai/gpt-oss-20b
 2026-01-12 09:09:20 +05:30
Chesars 0bc04ce129 fix: correct pricing for openrouter/openai/gpt-oss-20b 
Updated pricing from incorrect values to match OpenRouter's official rates:
- Input: $0.18/M → $0.02/M tokens (1.8e-07 → 2e-08)
- Output: $0.80/M → $0.10/M tokens (8e-07 → 1e-07)
 2026-01-10 19:39:04 +00:00
RobinandGitHub 0575bd2d1c feat: update prices json for novita provider (#18540) 
* feat: add novita models

* feat: ci

* feat: add novita support josn
 2026-01-10 00:48:06 +05:30
Cesar GarciaandGitHub c19c97591e fix: align max_tokens with max_output_tokens for consistency (#18820) 
* fix: align max_tokens with max_output_tokens for consistency

Fixed inconsistent max_tokens definitions in model_prices_and_context_window.json.
According to LiteLLM convention, max_tokens should equal max_output_tokens when available.

Models fixed:
- deepseek-chat: 131072 → 8192 (now equals max_output_tokens)
- dashscope/qwen-flash: 1000000 → 32768 (now equals max_output_tokens)
- databricks/databricks-gemma-3-12b: 128000 → 32000 (now equals max_output_tokens)

This ensures consistency across all providers where max_tokens represents
the maximum number of tokens that can be generated in the output.

* fix: align max_tokens with max_output_tokens for 244 models

- Fix 244 models where max_tokens != max_output_tokens
- Add test to validate max_tokens consistency and prevent regressions

According to model_prices_and_context_window.json spec:
- max_tokens is a LEGACY parameter
- Should always equal max_output_tokens when both are present

This ensures consistency across all model definitions.
 2026-01-10 00:37:45 +05:30
Cesar GarciaandGitHub 86b71d4713 fix(workflow): Update issue labeling with working regex pattern (#18821) 
* fix: align max_tokens with max_output_tokens for consistency

Fixed inconsistent max_tokens definitions in model_prices_and_context_window.json.
According to LiteLLM convention, max_tokens should equal max_output_tokens when available.

Models fixed:
- deepseek-chat: 131072 → 8192 (now equals max_output_tokens)
- dashscope/qwen-flash: 1000000 → 32768 (now equals max_output_tokens)
- databricks/databricks-gemma-3-12b: 128000 → 32000 (now equals max_output_tokens)

This ensures consistency across all providers where max_tokens represents
the maximum number of tokens that can be generated in the output.

* fix(workflow): Update issue labeling with working regex pattern

- Replace contains() with regex pattern using \s* for flexible whitespace matching
- Consolidate 4 separate steps into single unified component labeling step
- Tested and verified pattern works for all components: SDK, Proxy, UI Dashboard, Docs
- Pattern handles GitHub's issue body formatting with ### headers and variable newlines
 2026-01-08 23:48:41 +05:30
Emerson GomesandGitHub 6c00f6f342 Add support to zai glm-4.7 model in Vertex (#18782) 
* Add support to zai glm-4.7 model in Vertex

* Avoid failed on missing 'created' streaming chunk key
 2026-01-08 13:20:02 +05:30
Ishaan JaffandGitHub 3430325919 [Feat] Add Azure BFL - Flux 2 models (#18764) 
* add azure_ai/flux.2-pro

* get_flux2_image_generation_url

* azure_client_params

* docs
 2026-01-07 23:28:28 +05:30
Lundin MatthewsandGitHub 762345172c Add LlamaGate as a new provider (#18673) 
Adds LlamaGate (https://llamagate.dev) as an OpenAI-compatible provider with:
- Provider configuration in providers.json
- Documentation page with usage examples
- Model pricing for 17 models across categories:
  - General purpose (Llama 3.1/3.2, Mistral, Qwen, Dolphin)
  - Reasoning (DeepSeek R1, OpenThinker)
  - Code (Qwen Coder, DeepSeek Coder, CodeLlama)
  - Vision (Qwen VL, LLaVA, Gemma 3)
  - Embeddings (Nomic, Qwen3 Embedding)

Provider details:
- Base URL: https://api.llamagate.dev/v1
- Auth: Bearer token via LLAMAGATE_API_KEY
- Pricing: $0.02-$0.55 per 1M tokens
- All models are open-weights
 2026-01-07 00:00:30 +05:30
Isaac ReisandGitHub a17757159c add amazon.nova-2-multimodal-embeddings-v1:0 to model_prices_and_context_window.json (#18710) 2026-01-06 23:57:35 +05:30
Sameer Kankute 0cd92e895f fix model map 2026-01-06 18:14:00 +05:30
Sameer Kankute ffc462465d fix: remove display name 2026-01-06 16:31:07 +05:30
Sameer KankuteandGitHub 2baec27657 Revert "feat(model_cost): add display_name, model_vendor, and model_version metadata to model entries" 2026-01-06 15:29:42 +05:30
Sameer Kankute 9c795a2baa fix: test_all_models_have_display_name 2026-01-06 14:09:43 +05:30
Sameer Kankute a087df365e fix: test_aaamodel_prices_and_context_window_json_is_valid 2026-01-06 14:04:09 +05:30
Sameer KankuteandGitHub 694e44551f Merge pull request #17330 from nmgarza5/add-model-metadata 
feat(model_cost): add display_name, model_vendor, and model_version metadata to model entries
 2026-01-06 10:56:49 +05:30
0717376andGitHub 12f02f6c54 feat: Add GigaChat provider support (#18564) 
* feat: Add GigaChat provider support

Add native support for GigaChat API (Sber AI, Russia's leading LLM).

Supported features:
- Chat completions (sync/async)
- Streaming (sync/async)
- Function calling / Tools
- Structured output via JSON schema (emulated through function calls)
- Image input (base64 and URL)
- Embeddings

Closes #18515

* fix: resolve mypy type errors in GigaChat handler

- Fix _prepare_file_data return type (use 3-tuple for cleaner type flow)
- Add type annotations for lists in _process_content_parts methods
- Add type annotations in _collapse_user_messages
- Use ChatCompletionToolCallChunk for proper tool_use typing
- Add type: ignore[override] for astreaming async generator

* refactor(gigachat): migrate to BaseConfig pattern

* fix: remove unused imports

* fix: resolve mypy type errors

* fix: mypy type errors

* refactor: address review feedback for GigaChat provider

- Remove singleton pattern, reuse litellm HTTPHandler
- Move constants/errors to transformation files, delete common_utils.py
- Add models to model_prices_and_context_window.json
- Fix ssl_verify not passed to HTTP client for embeddings

* docs: update GigaChat documentation with ssl_verify requirement
 2026-01-06 10:10:02 +05:30
Nik 13db8e10dc feat: add display_name, model_vendor, and model_version metadata 2026-01-05 11:01:36 -08:00
Matt GreathouseandGitHub b24156079f Add gemini-3-flash on openrouter (#18247) 2026-01-05 16:37:23 +05:30
cantalupo555andGitHub 9b1c5f7e36 feat(zai): Add GLM-4.7 model with reasoning support (#18476) 
Add support for Z.AI GLM-4.7, latest flagship model with enhanced reasoning capabilities.

Changes:
- Add zai/glm-4.7 to model pricing with /bin/bash.60/M input, .20/M output
- Add cached input pricing (/bin/bash.11/M) for GLM-4.7
- Add supports_reasoning flag to enable thinking parameter
- Update ZAIChatConfig to support thinking parameter for models with reasoning
- Update documentation with GLM-4.7 as latest flagship model
- Add cached input column to pricing table (GLM-4.7 only)
- Add tests for GLM-4.7 reasoning support and cost calculation
- Update all examples to use GLM-4.7

Model specifications:
- Context: 200K input, 128K output
- Supports: reasoning, function calling, tool choice, prompt caching
- Pricing: Same as GLM-4.6 with cache support

See: https://docs.z.ai/guides/llm/glm-4.7
 2026-01-04 00:44:19 +05:30
Daniel YudelevichGitHubDaniel Yudelevich
 		af27c7d7ff fix: add deprecation_date for discontinued Google models (#18550) 
Add deprecation dates for Google models that have been discontinued
per https://ai.google.dev/gemini-api/docs/changelog:

- Gemini 1.5 Flash/Pro models: 2025-09-29
- imagen-3.0-generate-002: 2025-11-10
- veo-3.0 preview models: 2025-11-12
- gemini-2.0-flash image generation: 2025-11-14
- gemini-2.5-flash preview models: 2025-11-18
- gemini-2.0-flash-thinking-exp, pro previews: 2025-12-02
- gemini-2.0-flash-live-001: 2025-12-09
- text-embedding-004: 2026-01-14
- gemini-2.5-flash-image-preview: 2026-01-15

Co-authored-by: Daniel Yudelevich <yudelevi@users.noreply.github.com>
 2026-01-03 00:12:58 +05:30
Cesar GarciaandGitHub c8950a5ba2 fix(cost_calculator): correct gpt-image-1 cost calculation using token-based pricing (#17906) 
* fix(cost_calculator): correct gpt-image-1 cost calculation using token-based pricing (#13847)

gpt-image-1 uses token-based pricing (like chat models), not pixel-based pricing
like DALL-E. The old code was calculating incorrect costs by treating it as DALL-E.

Changes:
- Update model pricing JSON with correct token-based costs for gpt-image-1
- Add dedicated cost calculator for OpenAI gpt-image models
- Route gpt-image-1 to token-based calculator in cost router
- Add comprehensive tests for the new calculator

* refactor: simplify gpt-image-1 cost calculator using responses API helper

Reuse _transform_response_api_usage_to_chat_usage and generic_cost_per_token
for gpt-image-1 cost calculation since ImageUsage has the same spec as
ResponseAPIUsage.
 2026-01-02 23:08:52 +05:30
Sameer KankuteandGitHub ecbc678771 Merge pull request #18586 from BerriAI/litellm_fix_image_cost_track 
Add all resolution for gpt-image-1.5
 2026-01-02 20:58:59 +05:30
Sameer KankuteandGitHub bbb883ffa9 Merge pull request #18483 from yurekami/fix/deepseek-v3p2-pricing 
fix: correct deepseek-v3p2 pricing for Fireworks AI
 2026-01-02 17:09:12 +05:30
Sameer Kankute 6e91364004 Add all sizes and resolution for gpt-image-1.5 to model map 2026-01-02 15:40:52 +05:30
Alexsander HamirandGitHub 825c12149f [Fix] CI/CD - litellm_utils_testing (#18565) 2026-01-01 12:48:49 -08:00
yurekamiandClaude Opus 4.5 f5024624d7 fix: correct deepseek-v3p2 pricing for Fireworks AI 
Updated pricing for fireworks_ai/accounts/fireworks/models/deepseek-v3p2:
- input_cost_per_token: 1.2e-06 -> 5.6e-07 ($0.56/1M tokens)
- output_cost_per_token: 1.2e-06 -> 1.68e-06 ($1.68/1M tokens)

Pricing verified from https://fireworks.ai/models/fireworks/deepseek-v3p2

Fixes #17998

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-29 03:44:03 +09:00
mubashir1osmaniandGitHub 861b103dc0 added google image gen models 
added google image gen models
 2025-12-27 19:55:27 -05:00
mubashir1osmani 043d968c5a added google image gen models 2025-12-27 19:54:39 -05:00
MihidumandGitHub 73af18ba20 Add azure/gpt-5.2-chat (#18361) 
Add missing azure gpt-5.2-chat to match existing naming schemes
 2025-12-25 11:09:05 +05:30
Sameer Kankute c7e0366925 Add support for minmax tts 2025-12-23 21:53:53 +05:30
Sameer KankuteandGitHub d0fa01d13c Merge pull request #18377 from BerriAI/litellm_minmax_anthropic_spec 
Add anthropic native endpoint support for Minimax
 2025-12-23 21:49:27 +05:30
Sameer KankuteandGitHub fa14a9931f Merge pull request #18368 from BerriAI/litellm_together_ai_models_update 
Add supports_response_schema to all supported together ai models
 2025-12-23 17:27:11 +05:30
Sameer KankuteandGitHub 7559869359 Merge branch 'main' into litellm_minmax_anthropic_spec 2025-12-23 16:13:47 +05:30
Sameer Kankute 743960ad0a Add pricing for minmax models in model map 2025-12-23 16:10:06 +05:30
Emin AskerovandGitHub 73b64e53ff Add azure_ai/gpt-oss-120b model pricing details (#18317) 
Added pricing and configuration details for the azure_ai/gpt-oss-120b model, including costs and capabilities.
 2025-12-23 15:51:57 +05:30
Cesar GarciaandGitHub c4b2c570f0 feat(pricing): add Azure gpt-image-1.5 pricing to cost map (#18347) 
Add missing pricing entries for azure/gpt-image-1.5 and azure/gpt-image-1.5-2025-12-16 to model_prices_and_context_window.json.

These models use token-based pricing (same as OpenAI):
- Text input: $5.00/1M tokens
- Image input: $8.00/1M tokens
- Image output: $32.00/1M tokens
- Cached text: $1.25/1M tokens
- Cached image: $2.00/1M tokens
 2025-12-23 15:49:14 +05:30
Sameer KankuteandGitHub c47079ba3a Merge pull request #18062 from Chesars/fix/groq-deprecated-models 
fix: remove deprecated Groq models and update model registry
 2025-12-23 12:06:27 +05:30
Sameer Kankute ca635a5e38 Add supports_response_schema to all supported together ai models 2025-12-23 11:15:38 +05:30
Ishaan JaffandGitHub 2677d9d30d [Feat] New provider TTS - Add AWS polly API for TTS (#18326) 
* add aws_polly as new provider

* init AWSPollyTextToSpeechConfig

* test_aws_polly_tts_with_native_voice

* init aws_polly + AWS polly dispatch

* init AWSPollyTextToSpeechConfig

* fix transform

* add aws_polly as a new provider for TTS API

* add to sidebar

* docs aws polly

* code qa fix

* add AWS Polly Text-to-Speech

* add cost tracking for AWS polly

* docs fix
 2025-12-22 18:19:34 +05:30
Marty SullivanandGitHub b7fbf3cd7e add vertexai and gemini veo 3.1 ga models (#18303) 2025-12-22 12:04:44 +05:30
Sameer KankuteandGitHub 3761f38e43 Merge pull request #18254 from BerriAI/litellm_add_stability_model_edit_1 
Add support for stability model and bedrock stability model
 2025-12-20 00:23:15 +05:30
Sameer KankuteandGitHub d29f4cab59 Merge pull request #17971 from BerriAI/litellm_ocr_deepseek 
Add support for ocr for vertex ai deepseek model
 2025-12-20 00:13:57 +05:30
Sameer Kankute b849f51e58 Add support for stability model in image edit 2025-12-19 23:03:17 +05:30
Sameer Kankute b09ea08424 Add stability models for image edit 2025-12-19 23:03:17 +05:30
Will ChenandGitHub 3f686521ed Fix Gemini 3 Flash pricing for Vertex AI (#18202) 2025-12-19 01:13:04 +05:30
Alexsander HamirandGitHub f353bb6dba [Fix] CI/CD - litellm_mapped_tests_llms | litellm_mapped_tests_core | caching_unit_tests (#18197) 2025-12-18 08:49:23 -08:00