scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49
47338 commits 3118 branches 1436 tags 4.4 GiB
Commit graph

2021 commits

Author SHA1 Message Date
Mateo Wang
0318b4acdc
Merge pull request #30856 from emerzon/litellm_vertex_lyria_models 
feat(vertex): add Lyria model support
 2026-09-05 23:12:25 -07:00
mateo-berri
11e45ad953 fix(vertex_ai): mark the Lyria 3 catalog entries text-only 
`vertex_ai/lyria-3-clip-preview` and `vertex_ai/lyria-3-pro-preview` were
registered with `supports_vision`, `supports_image_input`, and an `image`
modality, which contradicts their `gemini/lyria-3-*` siblings and makes
/model/info advertise image input on text-to-music models.
 2026-09-05 23:00:01 -07:00
mateo-berri
6be78fa850 fix(vertex_ai): bill Lyria per generation, not per audio second 
Google prices Lyria per generated clip, so every Vertex Lyria entry in the
price map now carries a single output_cost_per_image and both the speech
and the passthrough cost paths read that one field. The old
output_cost_per_second and audio_seconds_per_prediction pair assumed a
30 second clip, which does not match the 32.768 second WAV Vertex returns,
and no other model in the map priced audio that way

Drops max_audio_length_hours and max_audio_per_prompt from the price map,
its schema, the generator, and ModelInfo, since nothing reads them, and
drops the audio_mime_type hidden param for the same reason: the response
already carries the resolved content type on its own header

Folds the per-model bundled catalog lookups into one cached parse of the
local cost map, validated with a TypeAdapter over a ReadOnly TypedDict
 2026-09-05 22:34:31 -07:00
Mateo Wang
56a61cf016
Merge pull request #39764 from BerriAI/litellm_govcloud_profiles_lit6421 
feat(pricing): add GovCloud pricing for every live but unpriced Bedrock model
 2026-09-05 17:15:22 -07:00
mateo-berri
8426235290 feat(ocr): add Cohere Parse support for cohere and azure_ai 2026-09-04 21:25:46 -07:00
mateo-berri
036d104533 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_govcloud_profiles_lit6421 2026-09-04 20:08:16 -07:00
mateo-berri
51514b9123 fix(cost-map): azure/gpt-6-astra accepts reasoning_effort none on Foundry 2026-09-04 17:29:55 -07:00
mateo-berri
3202963f25 feat(cost-map): add azure/gpt-6-astra and azure/us/gpt-6-astra Foundry pricing 2026-09-04 16:57:40 -07:00
mateo
50d6b26a86 fix(registry): mark baseten GLM-5.3 as vision-capable per Baseten vision docs 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 20:10:58 +00:00
mateo
1f0611a8b9 fix(registry): drop Together MiniMax M2.7 and revert Qwen2.5 7B Turbo pricing, both non-serverless 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 19:25:10 +00:00
mateo
7b96a11e5f feat(registry): add OpenRouter catalog gaps, Fireworks DeepSeek V4 Flash Vision, Together MiniMax M2.7 and Qwen2.5 7B Turbo pricing 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 19:19:08 +00:00
mateo-berri
bef3585d82 feat(pricing): add GovCloud rows for every live but unpriced Bedrock model 
Every model bedrock list-foundation-models and list-inference-profiles
report as live in us-gov-west-1 or us-gov-east-1 now has a priced row:
Claude Fable 5.1 (profile plus in-region), Nemotron Nano 9B (profile plus
in-region), Grok 4.6 (profile plus Mantle in both regions), the us-gov.
Claude 3 Haiku profile in the east, Nova Lite, Micro and the Nova 2
multimodal embeddings in the west, and the Gemma 4 and gpt-oss Mantle
SKUs the GovCloud offer files price. Offer-file rates are used where AWS
publishes them; Claude rows carry the 1.2x GovCloud premium.
 2026-09-04 10:03:43 -07:00
mateo
0c29f510bc fix(registry): drop gpt-image-2 text output price, add openrouter minimax-m3 and qwen3.7-plus 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 15:03:29 +00:00
mateo
c707f2fe5d fix(model_prices): databricks gpt-5-3-codex is served via the Responses API 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 14:32:11 +00:00
mateo
8e83d6d63d fix(model_prices): add Databricks Sep-2026 catalog, Azure gpt-realtime-2.x, per-token realtime image pricing 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 14:06:54 +00:00
mateo
08bfdadb10 chore: merge litellm_internal_staging into litellm_registry_audit_2026_09_02, drop the deleted ocr ledger 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-04 04:18:09 +00:00
mateo-berri
43f31b0a4b feat(pricing): add GovCloud Claude Opus 5 and us-gov. inference profile rows 2026-09-03 18:40:59 -07:00
mateo
f292667601 fix(registry): mark gpt-daybreak-*-latest as responses mode to match their Responses-only endpoints 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 21:41:12 +00:00
Mateo Wang
29ea2bd2cd
Merge pull request #39426 from BerriAI/litellm_azure_ai_grok_4_6_cost_map 
feat(azure_ai): add grok-4.6 to the model cost map
 2026-09-03 14:36:07 -07:00
mateo
00bdfe797a fix(registry): mark gemini-3.5-live-translate-preview as realtime with official token limits 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 21:16:55 +00:00
mateo
5a3a2f3d0a Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_registry_audit_2026_09_02 2026-09-03 21:09:30 +00:00
mateo
eae7b806e3 fix(registry): point Bedrock Qwen3 Coder 480B source at the us-west-2 on-demand price list 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 20:49:44 +00:00
mateo
080e364d5e fix(registry): carry Anthropic thinking/sampling flags on new Perplexity and OpenRouter Claude entries 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 20:28:48 +00:00
Mateo Wang
828d561fcc
Merge pull request #39622 from BerriAI/litellm_gpt_6_astra 
feat(models): add gpt-6-astra pricing and metadata
 2026-09-03 13:18:34 -07:00
mateo
2c4eb693ed fix(model_prices): absorb Baseten GLM-5.3 and OpenRouter live prices, fix Bedrock Qwen3 Coder 480B input price and Gemini Live image price 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 19:53:58 +00:00
mateo-berri
4991d0bf3e fix(models): match gpt-6-astra reasoning effort levels to OpenAI docs 
OpenAI documents low, medium, high, xhigh, and max for gpt-6-astra, with no none level, so the entry stops advertising none and starts advertising max.
 2026-09-03 12:47:25 -07:00
mateo-berri
897fba08c8 feat(models): add gpt-6-astra pricing and metadata 
Adds the OpenAI gpt-6-astra entry to both price files with standard, flex, priority (fast mode), batch, and above-272K long-context rates, and regression tests covering each tier and the batch rates.
 2026-09-03 12:47:25 -07:00
mateo
32a3a65312 fix(model_prices): add Lyria 3.5, Perplexity Agent API and OpenRouter first-party models, fix Nebius, Mistral, OpenRouter metadata 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 19:35:30 +00:00
mateo-berri
51d821ae45 fix(cost): bill bedrock_mantle web search at $12 per 1k queries using Bedrock's reported count 2026-09-03 12:21:54 -07:00
mateo
2c63095e83 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_registry_audit_2026_09_02 2026-09-03 19:02:19 +00:00
mateo-berri
a1e58aabe7 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_bedrock_mantle_web_search 2026-09-03 09:50:42 -07:00
mateo
840173e778 feat(registry): add azure_ai/mistral-ocr-4-0 page and annotation prices from Azure Retail Prices 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 13:48:25 +00:00
mateo
f26407aa8c feat(registry): add azure_ai/MAI-Thinking-1 from Azure Retail Prices and Foundry docs 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 13:43:48 +00:00
mateo
55a5f142e6 fix(model_prices): add azure_ai Codestral-2501 and FW-Nemotron-Lightning-3.5, sync Azure and Vertex deprecation dates, fix novita gpt-oss vision flags 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-03 13:23:02 +00:00
mateo
1a39275cb3 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_registry_audit_2026_09_02 2026-09-03 13:05:42 +00:00
Emerson Gomes
f18cb0cdb4
fix(vertex): make Lyria routing and billing data-driven 2026-09-02 19:22:42 -05:00
Emerson Gomes
b96844dd0c
feat(vertex): expose Lyria through audio speech 2026-09-02 19:22:15 -05:00
Emerson Gomes
514e9a1ee6
fix(vertex): address lyria review feedback 2026-09-02 19:19:53 -05:00
Emerson Gomes
3ead9d1688
feat(vertex): add Lyria model support 2026-09-02 19:19:52 -05:00
mateo-berri
c6b48af0d7 chore: merge litellm_internal_staging into litellm_azure_ai_grok_4_6_cost_map 2026-09-02 16:38:16 -07:00
mateo-berri
fe34124610 feat(azure_ai): add grok-4.6 to the model cost map 2026-09-02 16:03:45 -07:00
mateo
6fa02887c4 feat(model_prices): add meta/muse-spark-1.3 and its contributor tier 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-02 22:05:17 +00:00
mateo
e148868f0c fix(model_prices): set watsonx max_output_tokens from IBM's documented maximum new tokens 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-02 20:38:45 +00:00
mateo
671559e591 fix(model_prices): set watsonx max_tokens equal to max_output_tokens per registry convention 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-02 20:35:29 +00:00
mateo
60ffde65e0 fix(model_prices): drop unpriced Volcengine Seed 2.1 entries, they would record zero spend 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-02 20:08:43 +00:00
mateo
9c5b20abdd fix(model_prices): add Nebius, watsonx and Volcengine models and correct watsonx list prices 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-02 20:07:21 +00:00
mateo
7a8226e752 fix(model_prices): registry audit 2026-09-02, add claude-mythos-5-1 and gpt-daybreak aliases, fix gpt-5.5 Fast and W&B pricing 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-02 19:40:53 +00:00
mateo-berri
f38a1ec129 Merge branch 'litellm_internal_staging' of https://github.com/BerriAI/litellm into litellm_azure_deepseek_v4_flash_0731 
# Conflicts:
#	litellm/model_prices_and_context_window_backup.json
#	model_prices_and_context_window.json
 2026-09-02 11:43:22 -07:00
Mateo Wang
4049a075bd
Merge pull request #39170 from BerriAI/litellm_registry_audit_2026_09_01 
fix(models): registry audit 2026-09-01: openai realtime and long-context tiers, mistral aliases, voyage, xai, fireworks, together, scaleway, azure ai, govcloud, azure gov, cloudflare whisper, deprecation dates
 2026-09-02 11:02:43 -07:00
mateo-berri
a9d3a0746c fix(models): price Azure DeepSeek V4 Flash 0731 from its own meters under the catalog id 2026-09-02 10:59:11 -07:00