[GH-ISSUE #1102] [langchain]: why some model use only model = "model name" and some model like embedding and image generation model use model = "models/model_name" during init_chat_model() initialization ?? #145

Closed
opened 2026-02-17 17:19:16 -05:00 by yindo · 1 comment
Owner

Originally created by @SijanMahmudAI on GitHub (Oct 23, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/1102

Type of issue

issue / bug

Language

Python

Description

why some model use only model = "model name" and some model like embedding and image generation model use
model = "models/model_name" during init_chat_model() initialization ??
and also why there is no full list of all the models that supports by langchain?

Originally created by @SijanMahmudAI on GitHub (Oct 23, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/1102 ### Type of issue issue / bug ### Language Python ### Description why some model use only model = "model name" and some model like embedding and image generation model use model = "models/model_name" during init_chat_model() initialization ?? and also why there is no full list of all the models that supports by langchain?
yindo added the langchain label 2026-02-17 17:19:16 -05:00
yindo closed this issue 2026-02-17 17:19:16 -05:00
Author
Owner

@mdrxy commented on GitHub (Oct 31, 2025):

The difference in model naming conventions depends on the provider's API requirements

"models/" prefix is required by specific providers like Fireworks AI and some others

There's no single comprehensive list of all supported models because:

  1. Providers constantly add/remove models
  2. Each provider has their own model catalog that changes frequently
  3. Some models require special permissions or are region-specific
  4. A complete list would be impossible to keep current
@mdrxy commented on GitHub (Oct 31, 2025): The difference in model naming conventions depends on the provider's API requirements `"models/"` prefix is required by specific providers like Fireworks AI and some others There's no single comprehensive list of all supported models because: 1. Providers constantly add/remove models 2. Each provider has their own model catalog that changes frequently 3. Some models require special permissions or are region-specific 4. A complete list would be impossible to keep current
yindo changed title from [langchain]: why some model use only model = "model name" and some model like embedding and image generation model use model = "models/model_name" during init_chat_model() initialization ?? to [GH-ISSUE #1102] [langchain]: why some model use only model = "model name" and some model like embedding and image generation model use model = "models/model_name" during init_chat_model() initialization ?? 2026-06-05 17:25:20 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#145