Warning:
Your API key is exposed in the code. For security, please use environment variables instead.
Enter your OpenRouter API key:
Save Key
Advanced Parameters
▼
Basic Parameters
Temperature
0.0 - 2.0
Controls response randomness. Lower values are more focused and deterministic.
Top P
0.0 - 1.0
Limits token selection to the most likely tokens that sum to this probability.
Top K
Limits token selection to the K most likely tokens.
Max Tokens
Maximum number of tokens to generate in the response.
Advanced Parameters
Frequency Penalty
-2.0 - 2.0
Reduces repetition of tokens based on their frequency in the input.
Presence Penalty
-2.0 - 2.0
Reduces repetition of tokens regardless of their frequency.
Repetition Penalty
0.0 - 2.0
Penalizes repeated tokens in the output.
Seed
Seed for deterministic outputs. Leave empty for random.
Min P
0.0 - 1.0
Minimum probability threshold for token selection.
Top A
0.0 - 1.0
Alternate top sampling parameter.
Additional Features
Show Reasoning Tokens
Show Usage Information
Show Generation Metadata
Provider Preference
Any Provider
OpenAI
Anthropic
Google
Meta
Preferred model provider for routing.
Top Log Probabilities
Number of top log probabilities to return.
API Mode
API Mode
Chat Completion
Text Completion
Choose between chat and text completion modes.
Prompt
Enter your text prompt for completion mode.
Select a model...
Status:
Loading rate limit information...
AI is thinking...
Processing your request...
Cancel Response
📎 Attach Image
Send