Cesar Garcia a037414985 feat(deepseek): add native support for thinking and reasoning_effort params (#17712) ... * feat(deepseek): add native support for thinking and reasoning_effort params Add proper parameter mapping for DeepSeek thinking mode, allowing users to use the unified LiteLLM interface instead of extra_body workarounds. Supported formats: - thinking={"type": "enabled"} - thinking={"type": "enabled", "budget_tokens": X} (budget_tokens ignored) - reasoning_effort="low|medium|high" (maps to thinking enabled) DeepSeek only supports {"type": "enabled"} without budget_tokens, so any budget_tokens are stripped and all reasoning_effort values (except "none") map to enabled. Reference: https://api-docs.deepseek.com/guides/thinking_mode * docs(deepseek): add thinking and reasoning_effort parameter documentation		2025-12-11 15:28:43 -08:00
..
adding_provider	docs: fix strings	2025-12-05 09:37:22 -08:00
caching
completion	Merge pull request #17711 from BerriAI/litellm_add_additional_drop_params_support	2025-12-10 15:37:39 +05:30
contribute_integration	docs(community.md): add new integration partner doc	2025-12-09 18:17:14 -08:00
contributing	[Feat] Allow adding OpenAI compatible chat providers using .json + add public ai provider (#17448)	2025-12-04 17:59:25 -08:00
debugging
embedding	docs: improve Getting Started page and SDK documentation structure (#17614)	2025-12-08 13:05:50 -08:00
extras	docs: improve dev docs	2025-11-17 19:46:39 -08:00
guides	[docs] add docs for containers files api + code interpreter on LiteLLM (#17749)	2025-12-09 18:11:28 -08:00
integrations	docs(community.md): add new integration partner doc	2025-12-09 18:17:14 -08:00
langchain
observability	docs: Add SumoLogic integration documentation (#17647)	2025-12-08 18:54:07 -08:00
pass_through	Add batch passthrough endpoint cost tracking for anthropic	2025-12-10 18:24:31 +05:30
projects	docs: add Microsoft GraphRAG to projects using LiteLLM (#17616)	2025-12-06 13:47:46 -08:00
provider_registration	docs openai	2025-12-04 18:32:23 -08:00
providers	feat(deepseek): add native support for thinking and reasoning_effort params (#17712)	2025-12-11 15:28:43 -08:00
proxy	feat(guardrails): add configurable fail-open, timeout, and app_user to PANW Prisma AIRS guardrail (#17785)	2025-12-11 15:23:59 -08:00
search
secret_managers	fix: cyberark allow setting ssl verfiy to false (#17433)	2025-12-03 18:54:31 -08:00
tutorials	feat: add support for configurable confidence score thresholds and scope in Presidio PII masking (#17817)	2025-12-11 15:19:11 -08:00
vector_stores	Add vector store support for ragflow	2025-12-03 15:29:47 +05:30
a2a_agent_permissions.md	[Docs] A2a - Permission management (#17515)	2025-12-04 17:29:47 -08:00
a2a.md	[Docs] A2a - Permission management (#17515)	2025-12-04 17:29:47 -08:00
aiohttp_benchmarks.md
anthropic_count_tokens.md	Add /v1/messages/count_tokens endpoint documentation (#17772)	2025-12-10 11:34:11 -08:00
anthropic_unified.md
apply_guardrail.md
assistants.md	docs: improve Getting Started page and SDK documentation structure (#17614)	2025-12-08 13:05:50 -08:00
audio_transcription.md	Add support of audio transcription for OVHcloud (#17305)	2025-12-01 18:26:39 -08:00
batches.md	Litellm sameer nov 3 stable branch (#16963)	2025-11-22 09:35:05 -08:00
bedrock_converse.md
bedrock_invoke.md
benchmarks.md	docs: add missing details to benchmark comparison (#16690)	2025-11-15 20:12:32 -08:00
budget_manager.md
contact.md	docs: update broken Slack invite links to support page (#16546)	2025-11-12 12:41:55 -08:00
container_files.md	[docs] add docs for containers files api + code interpreter on LiteLLM (#17749)	2025-12-09 18:11:28 -08:00
containers.md	[docs] add docs for containers files api + code interpreter on LiteLLM (#17749)	2025-12-09 18:11:28 -08:00
contributing.md
data_retention.md
data_security.md
default_code_snippet.md
enterprise.md	docs: improve docs	2025-11-17 09:54:13 -08:00
exception_mapping.md
files_endpoints.md	Add support for file content download for bedrock batches	2025-12-04 13:27:53 +05:30
fine_tuning.md
generateContent.md
image_edits.md	Add Vertex AI Image Edit Support (#16828)	2025-11-19 18:39:28 -08:00
image_generation.md
image_variations.md
index.md	made litellm proxy and sdk difference cleaner in overview (#17790)	2025-12-10 19:14:49 -08:00
load_test_advanced.md
load_test_rpm.md
load_test_sdk.md
load_test.md
mcp_control.md	feat(proxy_server.py): preserve content field even if null (#16988)	2025-11-23 22:05:58 -08:00
mcp_cost.md
mcp_guardrail.md
mcp_usage.md
mcp.md	add strands tutorial (#17039)	2025-11-24 17:31:59 -08:00
migration_policy.md
migration.md
moderation.md
ocr.md
oidc.md
old_guardrails.md
projects.md
proxy_api.md
proxy_server.md
rag_ingest.md	[Feat] LiteLLM RAG API - Add support for Vertex RAG engine (#17117)	2025-11-26 15:49:04 -08:00
realtime.md
reasoning_content.md
rerank.md	feat(voyage): add rerank API support (#17744)	2025-12-09 17:34:09 -08:00
response_api.md	docs: improve Getting Started page and SDK documentation structure (#17614)	2025-12-08 13:05:50 -08:00
router_architecture.md
routing.md
rules.md
scheduler.md
sdk_custom_pricing.md
secret.md
set_keys.md
skills.md	[Docs] Claude Skills API (#17052)	2025-11-24 15:32:03 -08:00
text_completion.md
text_to_speech.md	Integrate eleven labs text-to-speech (#16573)	2025-11-24 18:49:30 -08:00
troubleshoot.md	docs: update broken Slack invite links to support page (#16546)	2025-11-12 12:41:55 -08:00
vector_store_files.md	fix docs	2025-11-15 16:58:47 -08:00
vertex_batch_passthrough.md
videos.md
wildcard_routing.md