Models¶
altimate supports models from all configured providers. Use the model and small_model fields to set defaults.
Configuration¶
The model format is provider/model-name.
small_model handles the small background requests that are not part of the conversation, such as the session title and prompt enhancement. When it is not set, Altimate Code picks a cheap model from the same provider (Claude Haiku, Gemini Flash or GPT-5 nano when the provider lists one) and otherwise uses the chat model. A small_model the provider cannot serve, or does not list, fails only those requests: chat keeps working, while new sessions keep their New session - <time> placeholder title until a retry succeeds. Altimate Code retries the title on each of the first five messages of a session and reports every failure in telemetry. A failure shows up as a failed to generate title line in the log, with the provider's error, and as a title_generation_failed telemetry event naming the model that was asked for; correct or remove the small_model value to resolve it.
Browsing Models¶
In the TUI:
| Action | Method |
|---|---|
| List all models | /models command |
| Model picker | Leader + m |
| Filter by provider | Leader + Shift+M |
Model Variants¶
Some providers offer model variants (e.g., different context lengths or capabilities):
{
"agent": {
"analyst": {
"model": "anthropic/claude-sonnet-4-6",
"variant": "extended-thinking"
}
}
}
Cycle through variants in the TUI with the variant cycle keybind.
Per-Agent Models¶
Set different models for different agents:
{
"model": "anthropic/claude-sonnet-4-6",
"agent": {
"analyst": {
"model": "anthropic/claude-haiku-4-5-20251001"
},
"builder": {
"model": "anthropic/claude-opus-4-6"
}
}
}
Tip
Use a fast, inexpensive model for the analyst agent (which runs many read-only queries) and a more capable model for the builder agent (which produces code).
Favorites¶
Mark models as favorites for quick cycling with the TUI keybind (leader + Shift+F).
Model Format Reference¶
Models are referenced as provider/model-name:
| Provider | Example Model |
|---|---|
| Anthropic | anthropic/claude-sonnet-4-6 |
| OpenAI | openai/gpt-4o |
| Amazon Bedrock | amazon-bedrock/anthropic.claude-sonnet-4-6-v1 |
| Azure | azure/gpt-4o |
google/gemini-2.5-pro |
|
| Ollama | ollama/llama3.1 |
| OpenRouter | openrouter/anthropic/claude-sonnet-4-6 |
| Copilot | copilot/gpt-4o |
| Snowflake Cortex | snowflake-cortex/claude-sonnet-4-6 |
| Custom | my-provider/my-model |
See Providers for full provider configuration details.