Differences

This shows you the differences between two versions of the page.

--- models [2026/04/11 14:46] – [Nemotron 3 Super] kat
+++ models [2026/04/20 06:52] (current) – kat
@@ Line 3: / Line 3: @@
 ===== Selection Criteria =====
+{{page>models:glm-5.1}}
 {{page>models:glm-5}}
 {{page>models:kimi-k25}}
 {{page>models:minimax-m25}}
 {{page>models:kimi-k2-thinking}}
 {{page>models:nemotron-3-super}}
-==== GLM 4.7 Flash ====
+{{page>models:glm-47-flash}}
+{{page>models:qwen-3.5}}
-''hf:zai-org/GLM-4.7-Flash''
+{{page>models:deepseek-v3.2}}
-**Price**: $0.10/mtok, $0.50/mtok
-By far the <wrap hi>cheapest model on Synthetic</wrap>. Capable at basic tasks like summarization, classification, simple translation of natural language commands into tool calls, or terminal commands.
-  * **Pros**: Cheapest. Very fast.
-  * **Cons**: Only for basic usage.
 ===== Embedding Models =====
-==== Nomic Embed ====
+{{page>models:nomic-embed-text-15}}
-''hf:nomic-ai/nomic-embed-text-v1.5''
-If you have a Synthetic subscription, using an embedding model is free. Embedding models are commonly used in vector databases to provide effective semantic search over your data. Think of it as an easy way to browse through a hundred documents without giving an agent the entire context.
-Nomic only works with text and is no longer state-of-the-art, so expect average performance.