LiteLLM now supports -latest model aliases
Same model name.
Newer models.
As providers release smarter, faster, cheaper models, you shouldn't have to update every app by hand.
LiteLLM now supports -latest aliases. Pick a model family once. We update the model behind the alias as newer versions arrive, so you can keep the same name in your code.
With litellm installed and OPENAI_API_KEY set:
from litellm import completion
response = completion(
model="openai/gpt-luna-latest",
messages=[{"role": "user", "content": "Say hello."}],
)
The same aliases work in the Python SDK and AI Gateway.
Supported models
Use the provider prefix with any of its aliases below, as in openai/gpt-luna-latest.
- OpenAI
openai/ gpt-luna-latest,gpt-sol-latest,gpt-terra-latest,gpt-astra-latest,gpt-mini-latest- Anthropic
anthropic/ claude-opus-latest,claude-sonnet-latest,claude-haiku-latest,claude-fable-latest- xAI
xai/ grok-latest- Moonshot
moonshot/ kimi-latest- Z.AI
zai/ glm-latest,glm-flash-latest- DeepSeek
deepseek/ deepseek-pro-latest,deepseek-flash-latest- DashScope
dashscope/ qwen-max-latest,qwen-flash-latest- MiniMax
minimax/ minimax-latest
These aliases call each provider's own API. Gemini and Mistral already offer provider-managed latest names, which LiteLLM passes through.
