scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78
46618 commits 4150 branches 1402 tags 2.2 GiB
Commit graph

1980 commits

Author SHA1 Message Date
Mateo Wang
d8595cb647
Merge pull request #38423 from BerriAI/litellm_gemini_latest_cache_read_rates 
fix(model_prices): bill gemini -latest/preview alias cache reads at 10% of input
 2026-08-26 17:25:24 -07:00
Mateo Wang
1ac39b10ba
Merge pull request #38412 from BerriAI/litellm_fix_gemini_tts_native_audio_rates 
fix(cost-map): correct Gemini TTS and native-audio rates
 2026-08-26 17:15:46 -07:00
Mateo Wang
b54f7505a3
Merge pull request #38419 from BerriAI/litellm_gemini_live_realtime_cost 
fix(cost): price gemini-live-2.5-flash-native-audio realtime sessions
 2026-08-26 17:15:41 -07:00
Mateo Wang
4e295e8eb9
Merge pull request #38422 from BerriAI/litellm_gemini35_flashlite_flex_cache_price 
fix(model_prices): correct gemini-3.5-flash-lite flex cache-read pricing
 2026-08-26 17:11:07 -07:00
mateo-berri
1e1c231076 fix(model_prices): bill gemini -latest/preview alias cache reads at 10% of input 2026-08-26 16:52:09 -07:00
mateo-berri
bd75c38e84 fix(model_prices): scope flash-lite flex cache-read cut to vertex entries 2026-08-26 16:48:32 -07:00
mateo-berri
dca5144dba Merge branch 'litellm_internal_staging' of https://github.com/BerriAI/litellm into litellm_gemini_maps_grounding_cost 
# Conflicts:
#	litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
 2026-08-26 16:27:40 -07:00
mateo-berri
0243c5dee4 fix(model_prices): correct gemini-3.5-flash-lite flex cache-read pricing 2026-08-26 16:25:15 -07:00
mateo-berri
ab1b7bf3b6 fix(cost): price gemini-live-2.5-flash-native-audio realtime sessions 
The GA vertex model had no cost map entry, and the realtime cost handler
accepted the router's price-less auto-registered deployment entry for the
session.created model at zero-defaulted rates, so sessions billed 0.0 even
when base_model pointed at the priced preview key. Adds the GA entry at its
published rates and makes the handler fall through zero-defaulted candidates
unless their cost map entry explicitly declares pricing.
 2026-08-26 15:53:37 -07:00
mateo-berri
241daa4cb7 Merge branch 'litellm_internal_staging' of https://github.com/BerriAI/litellm into litellm_gemini_maps_grounding_cost 
# Conflicts:
#	type-discipline-budget.json
 2026-08-26 15:33:28 -07:00
Mateo Wang
a8f3a74360
Merge pull request #38397 from BerriAI/litellm_deepseek_vision_forwarding 
fix: forward image content lists to DeepSeek vision models
 2026-08-26 15:32:25 -07:00
mateo-berri
b9a790899a fix(gemini): bill Google Maps grounding as its own SKU 
Gemini API Maps-grounded prompts were billed as web search and Vertex AI Maps-grounded prompts were not billed at all. Classify grounding metadata per candidate into web search vs Maps requests, carry a distinct google_maps_grounding_requests usage counter through non-streaming and streaming paths, and price it via the new google_maps_grounding_cost_per_query cost map key with per-query and per-prompt defaults keyed off web_search_billing_unit. Fixes #35906
 2026-08-26 15:31:27 -07:00
mateo-berri
d565860f60 fix(cost-map): correct gemini-live native-audio text input rate 2026-08-26 15:15:05 -07:00
mateo-berri
2548e960f1 fix(cost-map): correct Gemini TTS and native-audio rates 
Gemini 2.5 Flash Preview TTS, Gemini 2.5 Pro Preview TTS, and the three
gemini-2.5-flash-native-audio entries carried rates copied from the text
models, so audio output was billed 2x to 6x under Google's published
prices. Set the published per-token rates on all ten keys, add
output_cost_per_audio_token to the native-audio entries, and drop the
long-context tier rates Google does not publish for Pro TTS.
 2026-08-26 14:43:21 -07:00
mateo-berri
f772cad959 fix(cost-map): backfill prompt_cache_min_tokens for the remaining Claude 4.x re-export entries 2026-08-26 14:31:45 -07:00
mateo-berri
caa97eea22 fix(cost-map): correct prompt_cache_min_tokens for Claude Fable 5 and backfill Anthropic re-export entries 2026-08-26 14:00:39 -07:00
Yucheng Zhu
df7b1f0fce fix: forward image content lists to DeepSeek vision models 2026-08-26 13:08:22 -07:00
Devin AI
7c7af51185 merge: litellm_internal_staging into rolling registry branch 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-26 19:23:15 +00:00
Mateo Wang
74b6149d18
Merge pull request #38370 from BerriAI/litellm_azure_gpt_5_6_cache_write_pricing 
fix(pricing): add azure gpt-5.6 cache write rates and correct data zone priority
 2026-08-26 12:21:39 -07:00
Devin AI
4456a4407f fix(model_prices): azure gpt-5.6 cache writes, mistral missing models, together cache reads 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-26 19:20:14 +00:00
KnyazSh
736411bd67 Merge branch 'litellm_internal_staging' into feature/improve-gigachat-provider 2026-08-26 19:10:57 +00:00
mateo-berri
ece187ea24 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_anthropic_fast_mode_cache_and_response_speed 
# Conflicts:
#	tests/test_litellm/test_cost_calculator.py
 2026-08-26 12:10:33 -07:00
Mateo Wang
c13b278d79
Merge pull request #38369 from BerriAI/litellm_anthropic_geo_uplift_missing_models 
fix(cost-map): add US data residency uplift to claude-sonnet-4-6 and mythos entries
 2026-08-26 12:05:25 -07:00
Devin AI
0cc407a02d Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_registry_audit_bedrock_sol_anthropic_1hr 2026-08-26 19:02:56 +00:00
Mateo Wang
80843ae7cb
Merge pull request #38279 from 6matt/litellm_bedrock_converse_gpt5_reasoning_effort 
fix(bedrock): map reasoning_effort to reasoning.effort for OpenAI GPT-5.x on Converse
 2026-08-26 11:48:18 -07:00
Mateo Wang
2d3144c6c8
Merge pull request #38368 from BerriAI/litellm_fix_bedrock_mantle_gpt55_gpt54_context_window 
fix(model_prices): raise bedrock_mantle gpt-5.5 and gpt-5.4 max_input_tokens to Mantle's enforced 1050000
 2026-08-26 11:42:47 -07:00
mateo-berri
e97a84afcf fix(model_prices): add above-272k priority rates to azure us/eu gpt-5.6 entries 2026-08-26 11:40:19 -07:00
mateo-berri
8307be68c9 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_pr38100_tencent_thinking 2026-08-26 11:26:58 -07:00
mateo-berri
a0d1fef89d fix(anthropic): scale cache costs by fast mode and trust served speed 2026-08-26 11:24:12 -07:00
mateo-berri
b349b9bf50 fix(pricing): add azure gpt-5.6 cache write rates and correct data zone priority 2026-08-26 10:50:44 -07:00
mateo-berri
6416a97a4d fix(model_prices): price 1-hour cache writes on claude-3-haiku and claude-3-opus at 2x input 2026-08-26 10:48:49 -07:00
mateo-berri
a2cd2d8a4b fix(cost-map): add US data residency uplift to claude-sonnet-4-6 and mythos entries 2026-08-26 10:43:43 -07:00
mateo-berri
b97d5e77eb fix(model_prices): raise bedrock_mantle gpt-5.5 and gpt-5.4 max_input_tokens to Mantle's enforced 1050000 2026-08-26 10:42:00 -07:00
Devin AI
07c9812739 fix(model_prices): carry anthropic behavior flags on deepinfra claude entries, move retired together models to deprecated list 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-26 17:18:51 +00:00
Devin AI
d3ede97189 fix(model_prices): keep novita gpt-oss-120b vision flag per provider catalog 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-26 16:57:26 +00:00
Devin AI
d266326a42 fix(model_prices): azure gpt-4.1-nano retirement date, together deprecations, novita gpt-oss-120b vision flag, fireworks deepseek-v4-pro-0813 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-26 16:56:53 +00:00
Devin AI
9300018414 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_registry_audit_bedrock_sol_anthropic_1hr 2026-08-26 16:46:44 +00:00
mateo-berri
6fafb46731 fix(cost): apply Together AI cache read pricing and per-model registry rates 2026-08-25 16:45:50 -07:00
Matthew Lapointe
74e86d3c0d fix(bedrock): route reasoning_effort to reasoning.effort for OpenAI GPT-5.x on Converse 
OpenAI GPT-5.x models on Bedrock Converse expect reasoning effort under
additionalModelRequestFields as {"reasoning": {"effort": ...}}. They were
falling into the Anthropic branch and emitting a `thinking` block, which
Converse rejects with unknown_parameter.

The bedrock_converse gpt-5.6 entries were also missing supports_reasoning,
so reasoning_effort was dropped before mapping. Setting the flag lets the
existing config-driven supported-params path accept it, rather than adding
another model-name branch.
 2026-08-25 19:20:00 -04:00
Mateo Wang
d8d384eada
Merge pull request #38230 from BerriAI/litellm_together_models_backfill 
feat(models): add missing Together AI serverless models to the cost map
 2026-08-25 14:02:58 -07:00
Devin AI
fb15851f53 fix(model_prices): verified Novita, DeepInfra, W&B, Gemini cache-read and Fireworks registry fixes 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-25 19:16:14 +00:00
Devin AI
2b0c4c6c88 Merge litellm_internal_staging into registry audit branch 2026-08-25 19:02:49 +00:00
mateo-berri
44c7cb20ae feat(models): add missing Together AI serverless models to the cost map 
Backfill 21 serverless chat models, the multilingual-e5 embedding model, and
Llama-Guard-4-12B from the live Together catalog with per-token pricing and
capability flags. Mark 25 delisted together_ai entries with their documented
deprecation_date and point superseded models at a live successor via metadata.
Reprice Llama-3.3-70B-Instruct-Turbo to Together's current rate.
 2026-08-25 10:10:07 -07:00
mateo-berri
f583151a5b fix(model_prices): raise bedrock_mantle gpt-5.6 max_input_tokens to Mantle's enforced 1050000 2026-08-25 09:53:19 -07:00
Devin AI
ab160fb953 fix(model_prices): sync gpt-5.6-sol bedrock rates, add gpt-5.6-cyber, fix claude 3 1h cache writes 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-08-25 13:26:48 +00:00
Mateo Wang
da91d4b6c9
Merge pull request #38119 from BerriAI/litellm_bing_grounding_search_provider 
feat(search): add Grounding with Bing Search (bing_grounding) as a search provider
 2026-08-24 19:33:23 -07:00
Mateo Wang
d0da90ee6d
Merge pull request #38115 from BerriAI/litellm_fix_runwayml_video_provider 
fix(runwayml): route every generation endpoint and fix video cost tracking
 2026-08-24 12:35:59 -07:00
Felipe Rodrigues Gare Carnielli
c6b4cb93b7 refactor(tencent): capability-driven thinking coercion 
Address Greptile review comments and the strict lint budgets:
- read supports_adaptive_thinking from the model cost map instead of
  substring-matching the model name, so aliases and newly onboarded
  adaptive-only models need no code change
- add tencent/minimax-m3 to the pricing JSON (and backup), which also
  fixes cost tracking for the model
- type the thinking/extra_body payloads with ReadOnly TypedDicts
- build the merged extra_body without rebinding or in-place mutation
 2026-08-24 16:28:36 -03:00
mateo-berri
671a454baa Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_bing_grounding_search_provider 2026-08-24 11:53:45 -07:00
mateo-berri
a7cd2cd439 Merge branch 'litellm_internal_staging' into litellm_fix_46_thinking_budget 2026-08-24 11:31:10 -07:00