Models
The Opper platform integrates with most LLM providers and models
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
| Provider | Model | Region | Image In | Image Out | Audio In | Options |
|---|---|---|---|---|---|---|
| Azure | azure/dall-e-3-eu | EU | X | style: natural, vividquality: standard, hdsize: 1024x1024, 1792x1024, 1024x1792 | ||
| gcp/gemini-pro-1.5-eu | EU | X | X | |||
| gcp/imagen-3.0-generate-001-eu | EU | X | aspectRatio: 1:1, 3:4, 4:3, 16:9, 9:16 | |||
| Mistral | mistral/pixtral-12b-2409-eu | EU | X | |||
| OpenAI | openai/gpt4-turbo | US | X | |||
| OpenAI | openai/gpt-4o | US | X | |||
| OpenAI | openai/gpt-image-1 | US | X | X | quality: low, medium, high, autosize: 1024x1024, 1536x1024, 1024x1536, auto |
Embedding models
| Name | Provider | Location | Dimensions | Max Tokens |
|---|---|---|---|---|
| azure/text-embedding-ada-002 | Azure | EU | 1536 | 8192 |
| azure/text-embedding-3-large | Azure | EU | 3072 | 8191 |
| azure/text-embedding-3-large-1536 | Azure | EU | 1536 | 8191 |
| openai/text-embedding-ada-002 | OpenAI | US | 1536 | 8191 |
| openai/text-embedding-3-large | OpenAI | US | 1536 | 8191 |
| openai/text-embedding-3-small | OpenAI | US | 1536 | 8191 |
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:
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.