Opper supports a wide range of models and providers. We strive to make models available through European inference providers.

The following language and multi modal models are currently available in the platform:

Language models

Multimodal models

ProviderModelRegionImage InImage OutAudio InOptions
Azureazure/dall-e-3-euEUXstyle: natural, vivid
quality: standard, hd
size: 1024x1024, 1792x1024, 1024x1792
Googlegcp/gemini-pro-1.5-euEUXX
Googlegcp/imagen-3.0-generate-001-euEUXaspectRatio: 1:1, 3:4, 4:3, 16:9, 9:16
Mistralmistral/pixtral-12b-2409-euEUX
OpenAIopenai/gpt4-turboUSX
OpenAIopenai/gpt-4oUSX
OpenAIopenai/gpt-image-1USXXquality: low, medium, high, auto
size: 1024x1024, 1536x1024, 1024x1536, auto

Embedding models

NameProviderLocationDimensionsMax Tokens
azure/text-embedding-ada-002AzureEU15368192
azure/text-embedding-3-largeAzureEU30728191
azure/text-embedding-3-large-1536AzureEU15368191
openai/text-embedding-ada-002OpenAIUS15368191
openai/text-embedding-3-largeOpenAIUS15368191
openai/text-embedding-3-smallOpenAIUS15368191

Custom models and bring-your-own-key

Custom models can be added using the API or the Opper CLI. The README explains how to add a model, but here is an example of adding your own Azure deployment:

opper models create example/my-gpt4 azure/gpt4-production my-api-key-here '{"api_base": "https://my-gpt4-deployment.openai.azure.com/", "api_version": "2024-06-01"}'

This adds your custom deployment on my-gpt4-deployment.openai.azure.com and the model name gpt4-production using the my-api-key-here API key. This model is then accessible in Opper using the name example/my-gpt4.