AI Model Configuration

When you send a message in Askimo, it might feel like a single AI model is handling everything - but that is not the case. Behind the scenes, Askimo uses several specialized models simultaneously, each optimised for a different job. The model you pick in the main chat settings is only one of them.

Think of it like a team at a company: there is a senior consultant (your main chat model) who handles the deep thinking, and a set of fast specialists who handle smaller jobs in the background - like filing paperwork, reviewing photos, or searching the knowledge base - without consuming the senior consultant’s time or budget.

Askimo ships with sensible defaults for every provider so things work out of the box. But you can override each model independently to match your own priorities - whether that is lower cost, faster responses, higher accuracy, or complete local privacy.

Why Multiple Models?

Different tasks call for very different model characteristics:

Model Type	What it does	Why a dedicated model helps
Main Chat Model	Answers your questions, reasons, writes code	You choose this in the main provider settings
Utility Model	Fast background tasks - generating a chat title, detecting your intent, routing to the right tool	A small, cheap model is 10–100× faster and costs a fraction of the main model
Vision Model	Understands images you attach to a conversation	Must support multimodal input; may differ from the chat model
Image Model	Generates images from text prompts	Completely separate generation pipeline
Embedding Model	Converts text to vectors for semantic search	Powers RAG (Project Knowledge) and MCP tool matching

A practical example

Imagine you open Askimo, type a question, and attach a screenshot:

1. Utility model quickly reads your message and generates a short chat title in the sidebar.
2. Vision model analyses the screenshot you attached.
3. Main chat model receives both the text and the image analysis, then writes the full response.
4. If you have a project knowledge base open, the embedding model silently searches it for relevant context before the main model replies.

All of this happens in parallel, so you barely notice - but each step uses the model best suited for that job.

Overriding the defaults

Askimo’s defaults are chosen to work well for most users, but you may want to change them for reasons like:

• Cost - swap the utility model to the cheapest tier; it only writes short titles, so quality barely matters
• Speed - use a smaller, faster model for vision or utility tasks to reduce overall response time
• Accuracy - use a larger embedding model for more precise RAG results
• Privacy - point all models to a local Ollama instance so no data leaves your machine

---

Accessing Model Configuration

1. Open Settings (⌘ , on macOS / Ctrl , on Windows/Linux)
2. Go to the AI Providers tab
3. Your active provider’s Model Configuration card appears below the main provider settings

Each field saves automatically when you click away (you’ll see a ✓ checkmark confirm the save).

---

Model Configuration by Provider

You must configure your models

Cloud AI providers (OpenAI, Anthropic, Google, xAI) regularly deprecate older models and replace them with newer versions. Askimo does not ship with preset model defaults — you are required to enter the model names yourself to ensure you are always using a currently supported model. Check your provider’s documentation for the latest available models and update the utility, vision, image, and embedding fields accordingly.

OpenAI

OpenAI Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_OPENAI_MODELS
Utility Model		ASKIMO_OPENAI_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_OPENAI_UTILITY_TIMEOUT
Embedding Model	text-embedding-3-small	ASKIMO_OPENAI_EMBEDDING_MODEL
Vision Model		ASKIMO_OPENAI_VISION_MODEL
Image Model		ASKIMO_OPENAI_IMAGE_MODEL

Model deprecation

OpenAI periodically retires older models. When a model listed here is deprecated, Askimo will throw an error until you update the field with a supported replacement. Check the OpenAI model deprecation page and update any affected fields promptly.

Anthropic Claude

Anthropic Claude Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_ANTHROPIC_MODELS
Utility Model	claude-sonnet-4-6	ASKIMO_ANTHROPIC_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_ANTHROPIC_UTILITY_TIMEOUT
Embedding Model	(none - see note)	ASKIMO_ANTHROPIC_EMBEDDING_MODEL
Vision Model		ASKIMO_ANTHROPIC_VISION_MODEL
Image Model		ASKIMO_ANTHROPIC_IMAGE_MODEL

Note

Anthropic does not currently offer a standalone embedding model. The embedding field is intentionally left blank; Askimo will fall back to the configured embedding provider (e.g., OpenAI or Ollama) for RAG operations.

Model deprecation

Anthropic periodically retires older Claude models. When a model listed here is deprecated, Askimo will throw an error until you update the field with a supported replacement. Check the Anthropic model deprecation page and update any affected fields promptly.

Google Gemini

Google Gemini Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_GEMINI_MODELS
Utility Model		ASKIMO_GEMINI_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_GEMINI_UTILITY_TIMEOUT
Embedding Model		ASKIMO_GEMINI_EMBEDDING_MODEL
Vision Model		ASKIMO_GEMINI_VISION_MODEL
Image Model		ASKIMO_GEMINI_IMAGE_MODEL

Model deprecation

Google periodically retires Gemini models. When a model listed here is deprecated, Askimo will throw an error until you update the field with a supported replacement. Check the Google AI model versions page and update any affected fields promptly.

xAI (Grok)

xAI Grok Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_XAI_MODELS
Utility Model		ASKIMO_XAI_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_XAI_UTILITY_TIMEOUT
Embedding Model	(none - see note)	ASKIMO_XAI_EMBEDDING_MODEL
Vision Model		ASKIMO_XAI_VISION_MODEL
Image Model		ASKIMO_XAI_IMAGE_MODEL

Note

xAI does not currently provide a dedicated embedding model. Leave the embedding field empty and configure a separate provider (OpenAI or Ollama) for RAG.

Model deprecation

xAI periodically retires Grok models. When a model listed here is deprecated, Askimo will throw an error until you update the field with a supported replacement. Check the xAI model documentation and update any affected fields promptly.

Ollama

Ollama Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_OLLAMA_MODELS
Utility Model	(uses selected model)	ASKIMO_OLLAMA_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_OLLAMA_UTILITY_TIMEOUT
Embedding Model	nomic-embed-text:latest	ASKIMO_OLLAMA_EMBEDDING_MODEL
Vision Model		ASKIMO_OLLAMA_VISION_MODEL
Image Model		ASKIMO_OLLAMA_IMAGE_MODEL

Astuce

If Utility Model is left empty, Askimo uses your currently selected chat model for utility tasks. For better performance, pull a small dedicated model:

ollama pull qwen2.5:0.5b      # tiny & fast - great for utility tasks
ollama pull nomic-embed-text   # best-in-class local embedding
ollama pull llava              # vision model

LM Studio

LM Studio Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_LMSTUDIO_MODELS
Utility Model	(uses selected model)	ASKIMO_LMSTUDIO_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_LMSTUDIO_UTILITY_TIMEOUT
Embedding Model		ASKIMO_LMSTUDIO_EMBEDDING_MODEL
Vision Model		ASKIMO_LMSTUDIO_VISION_MODEL
Image Model		ASKIMO_LMSTUDIO_IMAGE_MODEL

Note

Model names must match exactly what LM Studio reports when the model is loaded. Check the LM Studio server log for the correct identifier.

LocalAI

LocalAI Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_LOCALAI_MODELS
Utility Model	(uses selected model)	ASKIMO_LOCALAI_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_LOCALAI_UTILITY_TIMEOUT
Embedding Model		ASKIMO_LOCALAI_EMBEDDING_MODEL
Vision Model		ASKIMO_LOCALAI_VISION_MODEL
Image Model		ASKIMO_LOCALAI_IMAGE_MODEL

Docker AI

Docker AI Model Configuration

Field	Default	Environment Variable
Available Models	(auto-detected)	ASKIMO_DOCKER_MODELS
Utility Model	(uses selected model)	ASKIMO_DOCKER_UTILITY_MODEL
Utility Timeout	45s	ASKIMO_DOCKER_UTILITY_TIMEOUT
Embedding Model	ai/qwen3-embedding:0.6B-F16	ASKIMO_DOCKER_EMBEDDING_MODEL
Vision Model		ASKIMO_DOCKER_VISION_MODEL
Image Model		ASKIMO_DOCKER_IMAGE_MODEL

---

Model Types Explained

Utility Model

The utility model handles fast, low-cost background tasks that don’t require the full power of your main chat model:

• Generating chat titles automatically
• Detecting user intent and routing to the correct tool
• Summarizing conversation context
• Running MCP tool classification

Best practice: Choose the smallest model that still produces coherent short text. For cloud providers this is typically a “mini” or “flash” tier model.

---

Vision Model

The vision model is called when you attach an image to a conversation. It must support multimodal (image + text) input.

• Analyzing screenshots and diagrams
• Reading text from images (OCR-style)
• Describing uploaded photos

Attention

If the vision model you configure does not support image input, image attachments will fail. Verify multimodal support in your provider’s model documentation before changing this value.

---

Image Model

The image model is used when Askimo generates images from a text prompt.

• Creating illustrations from descriptions
• Generating UI mockups or diagrams on request

Note

Image generation is only supported by providers that expose a dedicated image-generation endpoint (OpenAI DALL·E, Gemini image generation). For local providers, a Stable Diffusion backend must be running and configured.

---

Embedding Model

The embedding model converts text into vector representations used for semantic search. It powers:

• RAG (Project Knowledge) - finding relevant document chunks for your question
• Tool vector search - matching your intent to the right MCP tool

Astuce

Embedding model dimensions must be consistent within a project. If you switch embedding models, rebuild your RAG index from scratch (Settings → RAG → Rebuild Index) to avoid dimension mismatch errors.

Embedding support by provider:

Provider	Embedding Support	Notes
OpenAI	✅ Native	text-embedding-3-small (1536-d), text-embedding-3-large (3072-d)
Google Gemini	✅ Native	gemini-embedding-001 (3072-d)
Ollama	✅ Native	nomic-embed-text (768-d), mxbai-embed-large (1024-d)
Docker AI	✅ Native	ai/qwen3-embedding:0.6B-F16 (1536-d)
LM Studio	✅ Via server	Must load an embedding model in LM Studio
LocalAI	✅ Via server	Configure embedding backend in LocalAI
Anthropic Claude	❌ Not supported	Use another provider for embeddings
xAI (Grok)	❌ Not supported	Use another provider for embeddings

---

Troubleshooting

“Embedding dimension does not match store dimension”

You changed the embedding model after a RAG index was already built. The old index was created with a different vector size. Rebuild the index:

1. Go to Settings → RAG
2. Select the affected project
3. Click Rebuild Index

Utility tasks are slow

Your utility model may be too large. Switch to a smaller, faster model (e.g., gemini-2.5-flash-lite, gpt-4o-mini, claude-haiku-3-5, or a sub-1B local model).

Vision model returns an error for image attachments

The configured vision model does not support multimodal input. Check the provider’s documentation and update the vision model to one that accepts images.

Image generation is not available

Image generation requires provider-side support. Verify that your provider account has access to image generation endpoints and that the image model name is correct.