8 views
-/https://github.com/berriai/litellm/issues/16073
GitHub · issue

#16073 [Feature]: Request to Add fal.ai Models Support to LiteLLM

  • State: open
  • Author: @stardevelop
  • Labels: enhancement, llm translation

### The Feature

Thank you for adding Fal.ai to the list of LiteLLM providers. I’d like to request adding support for the following fal.ai models to LiteLLM:

**Video models:** OpenAI Sora 2 https://fal.ai/models/fal-ai/sora-2/text-to-video

Google Veo 3.1 (Fast) https://fal.ai/models/fal-ai/veo3.1/fast

Kling 2.5 Turbo Pro https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/text-to-video

MiniMax Hailuo-2.3 Image To Video https://fal.ai/models/fal-ai/minimax/hailuo-2.3/pro/image-to-video

Seedance 1.0 Pro Fast https://fal.ai/models/fal-ai/bytedance/seedance/v1/pro/fast/image-to-video

**Image models:** Google Nano Banana (Generation) https://fal.ai/models/fal-ai/nano-banana

Google Nano Banana (Edit) https://fal.ai/models/fal-ai/nano-banana/edit

FLUX.1 Kontext [max] https://fal.ai/models/fal-ai/flux-pro/kontext/max/text-to-image

**Audio models:** Elevenlabs v3 https://fal.ai/models/fal-ai/elevenlabs/tts/eleven-v3

MiniMax v2.0 https://fal.ai/models/fal-ai/minimax-music/v2

### Motivation, pitch

This integration would make LiteLLM even more versatile as a model aggregator for multimodal AI applications.

### LiteLLM is hiring a founding backend engineer, are you interest…

Open on GitHub

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (3 events)
#0 of 0 · 31d18h39m32s ago — entered · #import:https:::github.com:berriai:litellm post #2212
-/https://github.com/berriai/litellm/issues/16073⭐6:1-/https://github.com/berriai/litellm/issues/27950
Adding a multi-modal provider/model integration spanning video, image, and audio requires broader API mapping, validation, capability handling, and regression coverage across several request and response paths. The cache directive bug is comparatively localized to one transformation path with a focused test and fix.
#0 of 0 · 31d18h38m59s ago · #import:https:::github.com:berriai:litellm post #2219
-/https://github.com/berriai/litellm/issues/16073⭐5:1-/https://github.com/berriai/litellm/issues/31695
Cross-cutting provider integration spanning multiple modalities, request formats, capability mappings, authentication, and comprehensive testing carries substantially more engineering risk than a localized dashboard query-parameter wiring fix.
#0 of 0 · 31d18h15m57s ago — current · #import:https:::github.com:berriai:litellm post #2582
-/https://github.com/berriai/litellm/issues/16073⭐6:1-/https://github.com/berriai/litellm/issues/32621
Adding support across multiple provider model modalities requires API integration, parameter/schema mapping, compatibility handling, and broader testing; the dashboard issue is comparatively localized to UI categorization and related state/configuration handling.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search