scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81
46618 commits 2289 branches 1405 tags 2.4 GiB
Commit graph

1980 commits

Author SHA1 Message Date
Jay Prajapati
6a9d41234f
fix: allow tool_choice for Azure GPT-5 chat models (#19813) 
* fix: don't treat gpt-5-chat as GPT-5 reasoning

* fix: mark azure gpt-5-chat as supporting tool_choice

* test: cover gpt-5-chat params on azure/openai
 2026-01-27 17:51:13 -08:00
Sameer Kankute
c8a93c7d81
Merge pull request #19845 from BerriAI/litellm_gemini-robotics-er-1.5-preview2 
Add  Gemini Robotics-ER 1.5 preview support
 2026-01-27 17:47:44 +05:30
Sameer Kankute
c834d7d1fe
Merge branch 'main' into litellm_oss_staging_01_27_2026 2026-01-27 17:11:15 +05:30
Sameer Kankute
9a2750f8ec
Merge pull request #19617 from BerriAI/litellm_oss_staging_01_23_2026 
Litellm oss staging 01 23 2026
 2026-01-27 16:55:32 +05:30
Sameer Kankute
cf012a2f65 Add gemini-robotics-er-1.5-preview model in model map 2026-01-27 13:58:03 +05:30
Cesar Garcia
e4a557d95f
fix(xai): correct cached token cost calculation for xAI models (#19772) 
* fix(azure): use generic cost calculator for audio token pricing

Azure audio models were charging audio output tokens at the text token
rate instead of the correct audio token rate. This resulted in costs
being ~6.65x lower than expected.

The fix replaces Azure's custom cost calculation logic with the generic
cost calculator that properly handles text, audio, cached, reasoning,
and image tokens.

Fixes #19764

* fix(xai): correct cached token cost calculation for xAI models

- Fix double-counting issue where xAI reports text_tokens = prompt_tokens
  (including cached), causing tokens to be charged twice
- Add cache_read_input_token_cost to xAI grok-3 and grok-3-mini model variants
- Detection: when text_tokens + cached_tokens > prompt_tokens, recalculate
  text_tokens = prompt_tokens - cached_tokens

xAI pricing (25% of input for cached):
- grok-3 variants: $0.75/M cached (input $3/M)
- grok-3-mini variants: $0.075/M cached (input $0.30/M)
 2026-01-26 21:00:35 -08:00
Cesar Garcia
0d45b01069
fix(models): set gpt-5.2-codex mode to responses for Azure and OpenRouter (#19770) 
Fixes #19754

The gpt-5.2-codex model only supports the responses API, not chat completions.
Updated azure/gpt-5.2-codex and openrouter/openai/gpt-5.2-codex entries to use
mode: "responses" and supported_endpoints: ["/v1/responses"].
 2026-01-26 20:36:10 -08:00
Cesar Garcia
31a8d76d11
Update Gemini 2.0 Flash deprecation dates to March 31, 2026 (#19592) 
Google announced that Gemini 2.0 Flash and Flash Lite models will be discontinued on March 31, 2026. Updated deprecation_date field for all affected model variants across different providers (vertex_ai, gemini, deepinfra, openrouter, vercel_ai_gateway).

Models updated:
- gemini-2.0-flash (added deprecation date)
- gemini-2.0-flash-001 (updated from 2026-02-05)
- gemini-2.0-flash-lite (added deprecation date)
- gemini-2.0-flash-lite-001 (updated from 2026-02-25)

All variants now correctly reflect the March 31, 2026 shutdown date.
 2026-01-23 20:36:36 -08:00
John Greek
26a2c90818
[Fix] Anthropic models on Azure AI cache pricing (#19532) (#19614) 2026-01-22 20:00:40 -08:00
拐爷&&老拐瘦
3372430d40
Add pricing for volcengine models (deepseek-v3-2, glm-4-7, kimi-k2-thinking) (#19335) 
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 19:47:21 -08:00
Sameer Kankute
ad1edd38d5
Merge branch 'main' into litellm_staging_01_21_2026 2026-01-22 17:56:40 +05:30
Sameer Kankute
36f3250016
Merge pull request #19500 from Chesars/fix/audio-model-pricing 
fix(pricing): correct audio token costs for gpt-4o-audio-preview models
 2026-01-22 09:18:55 +05:30
Cesar Garcia
4106d24215
feat: add GMI Cloud provider support (#19376) 
* feat: add GMI Cloud provider support

Add GMI Cloud as an OpenAI-compatible provider with:
- Provider configuration in providers.json
- Documentation page with usage examples
- Model pricing for 16 models (Claude, GPT, DeepSeek, Gemini, etc.)
- Sidebar entry for docs navigation

* Add gmi_cloud to provider_endpoints_support.json

Add provider entry to pass CI validation check that ensures all
providers in openai_like/providers.json are documented.

* Fix provider key: gmi_cloud -> gmi

Match the provider key with providers.json

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
 2026-01-21 15:48:15 -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
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
540370a1aa
Merge pull request #19479 from BerriAI/litellm_sarvam_int 
Add support for sarvam models
 2026-01-21 19:03:52 +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
46c0f903a3 Add support for sarvam models 2026-01-21 15:17:26 +05:30
Sameer Kankute
9e1275b76c
Merge branch 'main' into litellm_staging_01_19_2026 2026-01-20 19:19:36 +05:30
Sameer Kankute
deb9142117
Merge pull request #19400 from BerriAI/main 
merge main iin 19/1 staging
 2026-01-20 16:45:01 +05:30
Sameer Kankute
cebcad48d3 Add gemini-2.5-computer-use-preview-10-2025 model for vertex ai provider 2026-01-20 15:53:02 +05:30
Connor Luebbehusen
d48df6c17d
fix: correct us.anthropic.claude-opus-4-5 In-region pricing (#19310) 2026-01-19 19:00:24 -08:00
Connor Luebbehusen
2ba7d2e821
fix: correct Groq gpt-oss pricing and add cache pricing (#19311) 2026-01-19 10:41:28 -08:00
Manuel Schweigert
29adf34313
Add ChatGPT subscription support and responses bridge (#19030) 
* Add ChatGPT subscription support and responses bridge

* Fix typing import for responses bridge

* Guard device code timestamp parsing

* add /v1/messages endpoint to chatgpt model
 2026-01-19 05:37:45 -08:00
Sameer Kankute
c5a8d4e34e
Merge branch 'main' into litellm_staging_01_16_2026 2026-01-19 18:11:21 +05:30
Ostap Bodnar
ce1a2c3209
add openai/dall-e base pricing entries (#19133) 2026-01-17 04:48:46 +05:30
YutaSaito
7aba0f738a
Revert "Litellm staging 01 15 2026" 2026-01-17 06:31:34 +09:00
Ishaan Jaffer
b86aae0212 fix stability mode 2026-01-16 09:08:11 -08:00
Sameer Kankute
48d1e769a8 Add azure/gpt-5.2-codex 2026-01-16 18:37:05 +05:30
Sameer Kankute
5782832b82
Merge pull request #19199 from BerriAI/litellm_fix_stability_issues1 
[Fix] Bedrock stability model usage issues
 2026-01-16 18:17:11 +05:30
Sameer Kankute
c76b527281 Fix model map 2026-01-16 17:17:21 +05:30
Sameer Kankute
f3ca05112e
Merge pull request #19206 from BerriAI/main 
merge main
 2026-01-16 15:22:16 +05:30
Sameer Kankute
4d45574fc5 fix Updated all 27 occurrences of mode: image_edit to mode: image_edits 2026-01-16 14:47:06 +05:30
Emerson Gomes
e8fa8c5fa1
fix gcp glm-4.7 pricing (#19172) 2026-01-15 18:35:40 -08:00
拐爷&&老拐瘦
92827ead65
Add pricing for volcengine models (deepseek-v3-2, glm-4-7, kimi-k2-thinking) (#19076) 
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-16 03:30:34 +05:30
Peter Dave Hello
62eee47618
Add support for OpenAI's gpt-5.2-codex (#19101) 
Reference:
- https://openai.com/index/introducing-gpt-5-2-codex/
- https://platform.openai.com/docs/models/gpt-5.2-codex
 2026-01-14 11:49:40 -08:00
Emerson Gomes
9f6fa4fb49
Fix Azure Grok prices (#19102) 2026-01-15 00:30:47 +05:30
Cesar Garcia
e0da7ca918
fix(models): correct max_input_tokens for GPT-5 models (#19056) 
OpenAI's 400k context window is split between input and output:
- GPT-5/5.1/5.2 models: 272k input + 128k output = 400k context
- GPT-5-pro models: 128k input + 272k output = 400k context

Reference: https://openai.com/index/introducing-gpt-5-for-developers/
"In the API, all GPT-5 models can accept a maximum of 272,000 input
tokens and emit a maximum of 128,000 reasoning & output tokens"

Fixes incorrect 400k max_input_tokens values across 32 models.
 2026-01-14 19:01:23 +05:30
Cesar Garcia
2b79d37e39
feat: Add Cerebras zai-glm-4.7 model support and deprecate zai-glm-4.6 (#18864) 
- Add cerebras/zai-glm-4.7 with same specs as 4.6 (128K context, $2.25/M input, $2.75/M output)
- Mark cerebras/zai-glm-4.6 with deprecation_date: 2026-01-20
- Both models support function calling, reasoning, and tool choice
 2026-01-13 19:45:02 -08:00
Cesar Garcia
a445d8a4b4
fix(pricing): correct cache_read pricing for gemini-2.5-pro models (#18157) 
- Fix cache_read_input_token_cost: 3.125e-07 → 1.25e-07 ($0.125/1M)
- Add cache_read_input_token_cost_above_200k_tokens: 2.5e-07 ($0.25/1M)

Models updated:
- gemini-2.5-pro
- gemini-2.5-pro-exp-03-25
- gemini-2.5-pro-preview-03-25
- gemini-2.5-pro-preview-05-06
- gemini-2.5-pro-preview-06-05
- gemini-2.5-pro-preview-tts
- gemini/gemini-2.5-pro
- gemini/gemini-2.5-pro-preview-03-25
- gemini/gemini-2.5-pro-preview-05-06
- gemini/gemini-2.5-pro-preview-06-05
- gemini/gemini-2.5-pro-preview-tts

Pricing source: https://ai.google.dev/gemini-api/docs/pricing
 2026-01-14 04:09:24 +05:30
nulone
478bdcb60b
fix(model_prices): sync DeepSeek chat/reasoner to V3.2 pricing (#18884) 2026-01-14 03:52:50 +05:30
Cesar Garcia
d03c5017ff
fix: correct context window sizes for GPT-5 model variants (#18928) 
* fix: correct context window sizes for GPT-5 model variants

Updates max_input_tokens for GPT-5, GPT-5.1, and GPT-5.2 model variants
to match OpenAI's official specifications, resolving issue #18927.

Changes:
- GPT-5.1 (base, codex variants): 272k → 400k tokens
- GPT-5.1-chat variants: 272k → 128k tokens (with max_output 16,384)
- GPT-5 (base): 272k → 400k tokens
- GPT-5-chat: 272k → 128k tokens (with max_output 16,384)
- GPT-5-codex: 272k → 400k tokens
- GPT-5-mini: 272k → 400k tokens
- GPT-5-nano: 272k → 400k tokens
- GPT-5-pro: 272k → 400k tokens (max_output 272k)
- GPT-5 dated versions (2025-08-07): 272k → 400k tokens

Affected providers: OpenAI, Azure (all regions), OpenRouter

Fixes #18927

* fix: correct Azure GPT-5 context window limits to match Azure docs

Azure OpenAI has different limits than OpenAI for GPT-5 models.

Changes:
- Azure GPT-5 models: max_input_tokens 400k → 272k (Azure limit)
- Azure GPT-5 Pro: max_output_tokens 272k → 128k (Azure limit)
- OpenAI GPT-5 models: remain at 400k (correct)
- OpenRouter models: remain at 400k (routes to OpenAI)

Azure docs specify 272k input + 128k output = 400k total context.
OpenAI allows full 400k input + 128k output.

* fix: correct Azure GPT-5 max_input_tokens to 272k

Azure has explicit input limit of 272k tokens (not 400k like OpenAI).
Context window 400k = 272k input + 128k output for Azure.
OpenAI allows flexible input up to 400k (context - output).
 2026-01-14 03:49:47 +05:30
Robin
b7c5662273
Fix: update novita models prices (#19005) 
* feat: ci

* feat: fix novita models prices
 2026-01-14 03:30:19 +05:30
Sameer Kankute
5a51b74658 Add pricing of azure_ai/claude-opus-4-5 2026-01-13 09:15:05 +05:30
Sameer Kankute
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 Kankute
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 Garcia
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 Kankute
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