Models
Manage your models and add custom models
Global Settings
GPT 4
128k
2.5
10
GPT 4o mini
128k
0.15
0.6
O1 preview
128k
15
60
O1 mini
128k
3
15
Deepseek Chat V3
64k
0.14
0.28
Deepseek Coder
64k
0.14
0.28
Deepseek Reasoner
64k
0.55
2.19
Claude 3.5 Sonnet
200k
3
15
Claude 3.5 Haiku
200k
0.8
4
Claude 3 Opus
200k
15
75
Claude 3 Sonnet
200k
3
15
xAI/Grok 2 Vision
8k
2
10
xAI/Grok 2
131k
2
10
xAI/Grok beta
131k
5
15
xAI/Grok vision beta
8k
5
15
Gemini 2.0 Flash Thinking Experimental
1m
1.25
5
Gemini 2.0 Flash Experimental
1m
1.25
5
Gemini 1.5 Pro
21m
1.25
5
Gemini 1.5 Flash
10m
0.07
0.3
Groq LLAMA3 70B
128k
0.59
0.79
Groq LLAMA3 8B instant
8k
0.05
0.1
Groq Mixtral 8x7B
8k
0.24
0.24
Default Model:
System Instruction:
Context Limit:
Temperature:
Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Top K:
Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. Min: 0
Top P:
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Presence Penalty:
How much to penalize new tokens based on whether they appear in the text so far. Increases the model's likelihood to talk about new topics.
Frequency Penalty:
Max Tokens:
The maximum number of tokens to generate before stopping.