Seven aliases on live routes
A -latest alias names a model family instead of a version. The default model list only shows models that can serve a request right now, and seven aliases are in it today. Each one resolves to the newest live model in its family:
| Alias | Resolves to (Oct 10, 2026) |
|---|---|
| google/gemini-flash-latest | google/gemini-3-flash |
| google/gemma-latest | google/gemma-4-31b |
| deepseek/deepseek-flash-latest | deepseek/deepseek-v4.1-flash |
| z-ai/glm-latest | z-ai/glm-5.3 |
| z-ai/glm-flash-latest | z-ai/glm-5.3-flash |
| moonshotai/kimi-latest | moonshotai/kimi-k3 |
| x-ai/grok-latest | x-ai/grok-4.7 |
The full alias list
The full catalog (/api/v1/models?all=1) lists 19 family aliases. That list resolves against every catalog model, including ones not routable at this moment, so its target can be newer than the live one. For example, it shows google/gemini-flash-latest as google/gemini-3.8-flash, while the live list resolves it to google/gemini-3-flash.
| Alias | Newest in full catalog |
|---|---|
| google/gemini-flash-latest | google/gemini-3.8-flash |
| google/gemini-flash-lite-latest | google/gemini-3.5-flash-lite |
| google/gemini-pro-latest | google/gemini-3.1-pro |
| google/gemma-latest | google/gemma-4-31b |
| deepseek/deepseek-latest | deepseek/deepseek-v4-pro |
| deepseek/deepseek-flash-latest | deepseek/deepseek-v4.1-flash |
| anthropic/claude-opus-latest | anthropic/claude-opus-5-5 |
| anthropic/claude-sonnet-latest | anthropic/claude-sonnet-5-5 |
| anthropic/claude-haiku-latest | anthropic/claude-haiku-5-5 |
| openai/gpt-latest | openai/gpt-5.5 |
| openai/gpt-mini-latest | openai/gpt-5.4-mini |
| openai/gpt-nano-latest | openai/gpt-5.4-nano |
| qwen/qwen-max-latest | qwen/qwen3.8-max |
| qwen/qwen-plus-latest | qwen/qwen3.7-plus |
| qwen/qwen-flash-latest | qwen/qwen3.8-flash |
| z-ai/glm-latest | z-ai/glm-5.3 |
| z-ai/glm-flash-latest | z-ai/glm-5.3-flash |
| moonshotai/kimi-latest | moonshotai/kimi-k3 |
| x-ai/grok-latest | x-ai/grok-4.7 |
openai/codex-mini-latest and openai/gpt-5-chat-latest also end in -latest, but they are OpenAI's own model ids, not AnyRouter family aliases.
What you see and pay
The response model field is the concrete model that answered, and billing uses that model's price. An alias can move to a newer model without notice, so pin a concrete id when you need stable behavior.
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "z-ai/glm-latest", "messages": [{"role": "user", "content": "Hello"}]}'- Launch post — why aliases exist and how fallback works.
- Docs — how aliases resolve.
Related posts
Latest aliases: name a family, always get a live model
Models get retired or go down. A -latest alias calls the newest model in a family that is available right now, skips dead ones, and bills the model that answered.
AnyRouter in October 2026: new models, top usage, free routes
A snapshot of the live catalog and the last 30 days of traffic: the newest models, what people route most, the anyrouter/* router ids, what is free right now, and one tip.
Route your first request in 2 minutes
Start free with your own keys, or top up and pay per token. Get $4/mo in credits and free models on Go — $2/mo, or free when you donate a provider key.
Start free