Sherlock AI models on CloudFerro Cloud

Sherlock AI supports inference with large language models, models with vision capabilities, and embedding models. Use the tables below to compare model families. Before calling the API, query the models endpoint and copy the exact returned model ID into the model field of your request.

The status labels describe catalogue entries; availability can change and must be checked for your project. Available identifies models offered for API requests. Models marked as Coming soon are listed for planning purposes but may not yet be available in your project. Models marked as Retiring should not be used for new integrations, because they are planned for removal or replacement.

Use a model ID in API requests

The selected model is specified in the request body. For example:

{
  "model": "speakleash/Bielik-11B-v3.0-Instruct",
  "messages": [
    {
      "role": "user",
      "content": "Explain what Sherlock AI is."
    }
  ]
}

Model IDs are case-sensitive. Replace the example ID if it is absent from the models endpoint response for your project.

Large language models

Table 15 Large language models
Status	Provider	Model ID	HF reference
Available	SpeakLeash Foundation	speakleash/Bielik-11B-v3.0-Instruct	Bielik-11B-v3.0-Instruct
Available	OpenAI	openai/gpt-oss-120b	openai/gpt-oss-120b
Available	Ministry of Digital Affairs of Poland	CYFRAGOVPL/PLLuM-12B-instruct	PLLuM-12B-instruct
Available	Meta	meta-llama/Llama-3.1-8B-Instruct	Llama-3.1-8B-Instruct
Available	Meta	meta-llama/Llama-3.3-70B-Instruct	Llama-3.3-70B-Instruct
Available	DeepSeek	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	DeepSeek-R1-Distill-Llama-70B
Available	MiniMaxAI	MiniMaxAI/MiniMax-M2.5	MiniMax-M2.5
Available	VillanovaAI	VillanovaAI/Villanova-2B-2512-Preview-Apnea-FT	Villanova-2B-2512-Preview-Apnea-FT
Coming soon	Mistral AI	mistralai/Mistral-Small-4-119B-2603	Mistral-Small-4-119B-2603
Coming soon	Google	google/gemma-4-31B-it	gemma-4-31B-it
Retiring	SpeakLeash Foundation	speakleash/Bielik-11B-v2.6-Instruct	Bielik-11B-v2.6-Instruct
Retiring	SpeakLeash Foundation	speakleash/Bielik-11B-v2.3-Instruct	Bielik-11B-v2.3-Instruct

Large language models with vision capabilities

Vision-capable models can process text prompts together with supported image inputs. Use them only when your workflow requires visual understanding; for text-only tasks, select one of the large language models listed above.

Table 16 Large language models with vision capabilities
Status	Provider	Model ID	HF reference
Retiring	Mistral AI	mistralai/Pixtral-12B-2409	Pixtral-12B-2409

Embedding models

Embedding models convert text into vector representations. They are commonly used for semantic search, retrieval-augmented generation, document matching, clustering, and similarity checks. Use an embedding model when you need vectors rather than a generated text answer.

Table 17 Embedding models
Status	Provider	Model ID	HF reference
Available	Intfloat	intfloat/e5-mistral-7b-instruct	intfloat/e5-mistral-7b-instruct
Available	BAAI	BAAI/bge-multilingual-gemma2	BAAI/bge-multilingual-gemma2
Available	NovaSearch	dunzhang/stella_en_1.5B_v5	dunzhang/stella_en_1.5B_v5
Coming soon	sdadas	sdadas/stella-pl-retrieval-8k	sdadas/stella-pl-retrieval-8k

Choosing a model

For general text generation, start with an available large language model and change the model only when you need a different language profile, context behavior, latency, or output quality. For image-aware tasks, use a vision-capable model if one is available in your project. For search and retrieval workflows, use an embedding model and send the resulting vectors to your own vector database or retrieval layer.

If an API request fails, check whether the model ID was copied exactly, whether the model is available in your Sherlock AI project, and whether you are using the correct endpoint for chat completions or embeddings.

What to do next

Continue with the Chat Playground guide.

Still need help?

If this article doesn’t answer all of your questions, our support team will do their best to help you.

Contact support