--- title: "Using Vision Models" url: "/en/docs/completion/vision" canonical_url: "https://docs.litellm.ai/en/docs/completion/vision" type: "docs" related: - "/en/docs/guides/multimodal_io" - "/en/docs/completion/audio" --- # Using Vision Models > Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt ## Quick Start Example passing images to a model **LiteLLMPython SDK** ```python import os from litellm import completion os.environ["OPENAI_API_KEY"] = "your-api-key" # openai call response = completion( model = "gpt-5.6-terra", messages=[ { "role": "user", "content": [ { "type": "text", "text": "What’s in this image?" }, { "type": "image_url", "image_url": { "url": "https://awsmp-logos.s3.amazonaws.com/seller-xw5kijmvmzasy/c233c9ade2ccb5491072ae232c814942.png" } } ] } ], ) ``` **LiteLLM Proxy Server** 1. Define vision models on config.yaml ```yaml model_list: - model_name: gpt-5.6-terra # OpenAI gpt-5.6-terra litellm_params: model: openai/gpt-5.6-terra api_key: os.environ/OPENAI_API_KEY - model_name: llava-hf # Custom OpenAI compatible model litellm_params: model: openai/llava-hf/llava-v1.6-vicuna-7b-hf api_base: http://localhost:8000 api_key: fake-key model_info: supports_vision: True # set supports_vision to True so /model/info returns this attribute as True ``` 2. Run proxy server ```bash litellm --config config.yaml ``` 3. Test it using the OpenAI Python SDK ```python import os from openai import OpenAI client = OpenAI( api_key="sk-", # your litellm proxy api key ) response = client.chat.completions.create( model = "gpt-5.6-terra", # use model="llava-hf" to test your custom OpenAI endpoint messages=[ { "role": "user", "content": [ { "type": "text", "text": "What’s in this image?" }, { "type": "image_url", "image_url": { "url": "https://awsmp-logos.s3.amazonaws.com/seller-xw5kijmvmzasy/c233c9ade2ccb5491072ae232c814942.png" } } ] } ], ) ``` ## Checking if a model supports `vision` **LiteLLM Python SDK** Use `litellm.supports_vision(model="")` -> returns `True` if model supports `vision` and `False` if not ```python keep-model-ids assert litellm.supports_vision(model="openai/gpt-5.6-terra") == True assert litellm.supports_vision(model="vertex_ai/gemini-3.1-pro-preview") == True assert litellm.supports_vision(model="openai/gpt-3.5-turbo") == False assert litellm.supports_vision(model="xai/grok-2-vision-latest") == True assert litellm.supports_vision(model="xai/grok-2-latest") == False ``` **LiteLLM Proxy Server** 1. Define vision models on config.yaml ```yaml model_list: - model_name: gpt-5.6-terra # OpenAI gpt-5.6-terra litellm_params: model: openai/gpt-5.6-terra api_key: os.environ/OPENAI_API_KEY - model_name: llava-hf # Custom OpenAI compatible model litellm_params: model: openai/llava-hf/llava-v1.6-vicuna-7b-hf api_base: http://localhost:8000 api_key: fake-key model_info: supports_vision: True # set supports_vision to True so /model/info returns this attribute as True ``` 2. Run proxy server ```bash litellm --config config.yaml ``` 3. Call `/model_group/info` to check if your model supports `vision` ```shell curl -X 'GET' \ 'http://localhost:4000/model_group/info' \ -H 'accept: application/json' \ -H "x-api-key: $LITELLM_API_KEY" ``` Expected Response ```json { "data": [ { "model_group": "gpt-5.6-terra", "providers": ["openai"], "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supports_vision": true, # 👈 supports_vision is true "supports_function_calling": true }, { "model_group": "llava-hf", "providers": ["openai"], "max_input_tokens": null, "max_output_tokens": null, "mode": null, "supports_vision": true, # 👈 supports_vision is true "supports_function_calling": false } ] } ``` ## Explicitly specify image type If you have images without a mime-type, or if litellm is incorrectly inferring the mime type of your image (e.g. calling `gs://` url's with vertex ai), you can set this explicitly via the `format` param. ```json "image_url": { "url": "gs://my-gs-image", "format": "image/jpeg" } ``` LiteLLM will use this for any API endpoint, which supports specifying mime-type (e.g. anthropic/bedrock/vertex ai). For others (e.g. openai), it will be ignored. **SDK** ```python import os from litellm import completion os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # openai call response = completion( model = "claude-sonnet-5", messages=[ { "role": "user", "content": [ { "type": "text", "text": "What’s in this image?" }, { "type": "image_url", "image_url": { "url": "https://awsmp-logos.s3.amazonaws.com/seller-xw5kijmvmzasy/c233c9ade2ccb5491072ae232c814942.png", "format": "image/jpeg" } } ] } ], ) ``` **PROXY** 1. Define vision models on config.yaml ```yaml model_list: - model_name: gpt-5.6-terra # OpenAI gpt-5.6-terra litellm_params: model: openai/gpt-5.6-terra api_key: os.environ/OPENAI_API_KEY - model_name: llava-hf # Custom OpenAI compatible model litellm_params: model: openai/llava-hf/llava-v1.6-vicuna-7b-hf api_base: http://localhost:8000 api_key: fake-key model_info: supports_vision: True # set supports_vision to True so /model/info returns this attribute as True ``` 2. Run proxy server ```bash litellm --config config.yaml ``` 3. Test it using the OpenAI Python SDK ```python import os from openai import OpenAI client = OpenAI( api_key="sk-", # your litellm proxy api key ) response = client.chat.completions.create( model = "gpt-5.6-terra", # use model="llava-hf" to test your custom OpenAI endpoint messages=[ { "role": "user", "content": [ { "type": "text", "text": "What’s in this image?" }, { "type": "image_url", "image_url": { "url": "https://awsmp-logos.s3.amazonaws.com/seller-xw5kijmvmzasy/c233c9ade2ccb5491072ae232c814942.png", "format": "image/jpeg" } } ] } ], ) ``` ## Spec ``` "image_url": str OR "image_url": { "url": "url OR base64 encoded str", "detail": "openai-only param", "format": "specify mime-type of image" } ``` ## Related pages - [Multimodal I/O](https://docs.litellm.ai/en/docs/guides/multimodal_io.md) - [Using Audio Models](https://docs.litellm.ai/en/docs/completion/audio.md)