ComfyUI Node: LiteLLMModelProviderAdv
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
ETK/LLM/LiteLLM
Inputs
name
- openai/gpt-3.5-turbo ($2.00/1M tokens)
- openai/gpt-3.5-turbo-16k (Input: $3.00/1M, Output: $4.00/1M tokens)
- openai/gpt-4 (Input: $30/1M, Output: $60/1M tokens (8K))
- openai/gpt-4-32k (Input: $60/1M, Output: $120/1M tokens (32K))
- openai/gpt-4o (Input: $2.50/1M, Cached: $1.25/1M, Output: $10.00/1M tokens)
- openai/gpt-4o-2024-08-06 (Input: $2.50/1M, Cached: $1.25/1M, Output: $10.00/1M tokens)
- openai/gpt-4o-audio-preview (Input: $2.50/1M, Output: $10.00/1M tokens)
- openai/gpt-4o-audio-preview-2024-12-17 (Input: $2.50/1M, Output: $10.00/1M tokens)
- openai/gpt-4o-mini (Input: $0.15/1M, Cached: $0.075/1M, Output: $0.60/1M tokens)
- openai/gpt-4o-mini-2024-07-18 (Input: $0.15/1M, Cached: $0.075/1M, Output: $0.60/1M tokens)
- openai/gpt-4o-mini-audio-preview (Input: $0.15/1M, Output: $0.60/1M tokens)
- openai/gpt-4o-mini-audio-preview-2024-12-17 (Input: $0.15/1M, Output: $0.60/1M tokens)
- openai/gpt-4o-mini-realtime-preview (Input: $0.60/1M, Cached: $0.30/1M, Output: $2.40/1M tokens)
- openai/gpt-4o-mini-realtime-preview-2024-12-17 (Input: $0.60/1M, Cached: $0.30/1M, Output: $2.40/1M tokens)
- openai/gpt-4o-realtime-preview (Input: $5.00/1M, Cached: $2.50/1M, Output: $20.00/1M tokens)
- openai/gpt-4o-realtime-preview-2024-12-17 (Input: $5.00/1M, Cached: $2.50/1M, Output: $20.00/1M tokens)
- openai/gpt-5 (Input: $10.00/1M, Cached: $5.00/1M, Output: $40.00/1M tokens)
- openai/gpt-5-mini (Input: $1.00/1M, Cached: $0.50/1M, Output: $4.00/1M tokens)
- openai/gpt-5-mini-preview (Input: $1.00/1M, Cached: $0.50/1M, Output: $4.00/1M tokens)
- openai/gpt-5-preview (Input: $10.00/1M, Cached: $5.00/1M, Output: $40.00/1M tokens)
- openai/o1 (Input: $15.00/1M, Cached: $7.50/1M, Output: $60.00/1M tokens)
- openai/o1-2024-12-17 (Input: $15.00/1M, Cached: $7.50/1M, Output: $60.00/1M tokens)
- openai/o1-mini (Input: $1.10/1M, Cached: $0.55/1M, Output: $4.40/1M tokens)
- openai/o1-mini-2024-09-12 (Input: $1.10/1M, Cached: $0.55/1M, Output: $4.40/1M tokens)
- openai/o3-mini (Input: $1.10/1M, Cached: $0.55/1M, Output: $4.40/1M tokens)
- openai/o3-mini-2025-01-31 (Input: $1.10/1M, Cached: $0.55/1M, Output: $4.40/1M tokens)
- anthropic/claude-3-haiku-20240307
- anthropic/claude-3-sonnet-20240229
- anthropic/claude-3-opus-20240229
- anthropic/claude-3-5-sonnet-20240620
- bedrock/anthropic.claude-3-haiku-20240307-v1:0
- bedrock/anthropic.claude-3-sonnet-20240229-v1:0
- bedrock/anthropic.claude-3-opus-20240229-v1:0
- bedrock/anthropic.claude-3-5-sonnet-20240620
- vertex_ai/gemini-1.5-pro-preview-0514
- vertex_ai/gemini-1.5-flash-preview-0514
- vertex_ai/meta/llama3-405b-instruct-maas
- together_ai/deepseek-ai/DeepSeek-V3
- together_ai/meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
Outputs
LITELLM_MODEL
Extension: ComfyUI_LiteLLM
Nodes for calling LLMs, enabled by LiteLLM
Authored by Hopping-Mad-Games
Looking for a different node?
More nodes in ComfyUI_LiteLLM
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.