public/index.html
Click slider numbers to input manually.
MAD LAB MODE ON
Kobold Presets
GUI KoboldAI Settings
NovelAI Presets
Default
Chat Completion Presets
Default
Text Completion presets
Response (tokens)
Streaming
Streaming
Streaming
Context (tokens)
Unlocked
Max prompt cost: –
AI Module
Changes the style of the generated text. No ModuleInstructProse AugmenterText Adventure
Temperature
Repetition Penalty
Rep Pen Range
Repetition Penalty Slope
Repetition Penalty Frequency
Repetition Penalty Presence
Min P
TFS
Top P
Top A
Top K
Mirostat Tau
Mirostat LR
Typical P
Linear
Quad
Conf
Min Length
Phrase Repetition Penalty OffVery lightLightMediumAggressiveVery aggressive
Preamble
Use style tags to modify the writing style of the output.
Banned Tokens
Sequences you don't want to appear in the output. One per line. Text or [token ids].
Logit Bias Add
Helps to ban or reinforce the usage of certain tokens.
Unlocked Context Size Unrestricted maximum value for the context size slider. Enable only if you know what you're doing.
Context Size (tokens)
Max Response Length (tokens)
Multiple swipes per generation
Middle-out Transform
AutoAllowForbid
Max prompt cost: Unknown
Max prompt cost: Unknown
Max prompt cost: Unknown
Streaming
Display the response bit by bit as it is generated.
When this is off, responses will be displayed all at once when they are complete.
Temperature
Frequency Penalty
Presence Penalty
Top K
Top P
Repetition Penalty
Min P
Top A
Quick Prompts Edit
Main
Auxiliary
Post-History Instructions
Utility Prompts
Impersonation prompt
Prompt that is used for Impersonation function
World Info format template
Wraps activated World Info entries before inserting into the prompt.Use{0}to mark a place where the content is inserted.
Scenario format template
Use {{scenario}} to mark a place where the content is inserted.
Personality format template
Use {{personality}} to mark a place where the content is inserted.
Group Nudge prompt template
Sent at the end of the group chat history to force reply from a specific character.
New Chat
Set at the beginning of the chat history to indicate that a new chat is about to start.
New Group Chat
Set at the beginning of the chat history to indicate that a new group chat is about to start.
New Example Chat
Set at the beginning of Dialogue examples to indicate that a new example chat is about to start.
Continue nudge
Set at the end of the chat history when the continue button is pressed.
Replace empty message
Send this text instead of nothing when the text box is empty.
Seed
Set to get deterministic results. Use -1 for random seed.
Temperature
Top K
Top P
Typical P
Min P
Top A
TFS
Repetition Penalty
Rep Pen Range
Repetition Penalty Slope
Mode
Tau
Eta
Ban EOS Token
Seed
Samplers Order
Samplers will be applied in a top-down order. Use with caution.
Top K0
Top A1
Top P & Min P2
Tail Free Sampling3
Typical P4
Temperature5
Repetition Penalty6
Load koboldcpp order
Samplers Order
Samplers will be applied in a top-down order. Use with caution.
Temperature0
Top K Sampling1
Nucleus Sampling2
Tail Free Sampling3
Top A Sampling4
Typical P5
Mirostat8
Unified Sampling9
Min P10
Neutralize Samplers
Sampler Select
Multiple swipes per generation
Temperature
Top K
Top P
Typical P
Min P
Top A
TFS
Epsilon Cutoff
Top nsigma
Min Keep
Eta Cutoff
Repetition Penalty
Rep Pen Range
Rep Pen Slope
Rep Pen Decay
Encoder Penalty
Frequency Penalty
Presence Penalty
No Repeat Ngram Size
Skew
Min Length
Maximum tokens/second
Target
Decay
Smoothing Factor
Smoothing Curve
Threshold
Probability
Multiplier
Base
Allowed Length
Penalty Range
Sequence Breakers
Minimum Temp
Maximum Temp
Exponent
Mode
Tau
Eta
Length Penalty
Early Stopping
Penalty Alpha
Do SampleAdd BOS Token
Ban EOS Token
Ignore EOS Token
Skip Special TokensRequest Model ReasoningTemperature Last
Speculative Ngram
Spaces Between Special Tokens
Seed
Banned Tokens/Strings
Global list
Preset-specific list
Add
Helps to ban or reinforce the usage of certain tokens.
Scale
Negative Prompt
Allow empty schema objects
Samplers Order
kcpp only. Samplers will be applied in a top-down order. Use with caution.
Top K0
Top A1
Top P & Min P2
Tail Free Sampling3
Typical P4
Temperature5
Repetition Penalty6
Load default order
llama.cpp only. Determines the order of samplers. If Mirostat mode is not 0, sampler order is ignored.
Temperature
Top K
Top P
Typical P
Min P
Exclude Top Choices
DRY
Rep/Freq/Pres Penalties
Top N-Sigma
Load default order
Ooba only. Determines the order of samplers.
Repetition Penalty
Presence Penalty
Frequency Penalty
DRY
Temperature
Dynamic Temperature
Quadratic / Smooth Sampling
Top Nsigma
Top K
Top P
Typical P
Epsilon Cutoff
Eta Cutoff
Tail Free Sampling
Top A
Min P
Adaptive-P
Mirostat
XTC
Encoder Repetition Penalty
No Repeat Ngram
Load default order
Aphrodite only. Determines the order of samplers.
DRY
Penalties
No Repeat Ngram
Dynatemp & Temperature
Top Nsigma
Top P & Top K
Top A
Min P
Tail-Free Sampling
Eta Cutoff
Epsilon Cutoff
Typical P
Cubic and Quadratic Sampling
XTC
Load default order
Character Names Behavior ()
None Never add character name prefixes. May behave poorly in groups, choose with caution. Default Add prefixes for groups and past personas. Otherwise, make sure you provide names in the prompt. Completion Object Add character names to completion objects. Restrictions apply: only Latin alphanumerics and underscores. Message Content Prepend character names to message contents.
Continue Postfix ()
NoneSpaceNewlineDouble Newline
Continue prefill Continue sends the last message as assistant role instead of system message with instruction.
Squash system messages Combines consecutive system messages into one (excluding example dialogues). May improve coherence for some models.
Use system prompt Send the system prompt for supported models. If disabled, the user message is added to the beginning of the prompt.
Enable web search Use search capabilities provided by the backend. Not free, adds a $0.02 fee to each prompt.
Enable function calling
Allows using function tools. Can be utilized by various extensions to provide additional functionality. Not supported when Prompt Post-Processing with "no tools" is used!
Tool Call Recurse Limit
Interleaved Thinking DisabledSince Last User MessageActive Tool Chain
Sends reasoning from preceding assistant turns with tool-call requests to maintain interleaved thinking context.
Enable "Request model reasoning" to use Interleaved Thinking.
Send inline media
Sends attached media in prompts if supported by the model. Videos must be less than 20 MB and under 1 minute long.** Audio must be less than 20 MB.**
Inline Image Quality AutoLowHigh
Request inline images
Allows the model to return image attachments. Incompatible with the following features: function calling, web search, system prompt.
ResolutionAuto1K2K4K
Aspect RatioAuto1:19:1616:93:44:33:22:35:44:521:9
Request model reasoning Allows the model to return its thinking process. This setting affects visibility only.
Reasoning EffortAutoMinimumLowMediumHighMaximum OpenAI-style options: low, medium, high. Minimum and maximum are aliased to low and high. Auto does not send an effort level. Request model reasoning = Off with Reasoning Effort = Minimum disables reasoning entirely on models that support that, but can cause errors with some models. Allocates a portion of the response length for thinking (min: 1024 tokens, low: 10%, medium: 25%, high: 50%, max: 95%), but minimum 1024 tokens. Auto does not request thinking.
Sets a dynamic reasoning depth level for thinking (Flash 3/Pro 3). High and low are supported by both, minimal and medium are Flash 3 only. Auto lets the model decide.
Allocates a portion of the response length for thinking (Flash 2.5/Pro 2.5) (min: 0/128 tokens, low: 10%, medium: 25%, high: 50%, max: 24576/32768 tokens). Auto lets the model decide.
VerbosityAutoLowMediumHigh Constrains the verbosity of the model's response. On Opus 4.6 / Sonnet 4.6, a non-automatic Reasoning Effort takes precedence over Verbosity.
Assistant Prefill
Assistant Impersonation Prefill
Prefills won't work when function calling is enabled and any tools are registered.
Logit Bias
Helps to ban or reinforce the usage of certain tokens.Confirm token parsing withTokenizer.
View / Edit bias preset
Add bias entry
Most tokens have a leading space.
Text CompletionChat CompletionNovelAIAI HordeKoboldAI Classic
Adjust context size to worker capabilitiesAdjust response length to worker capabilitiesTrusted workers onlyContext: --, Response: --
Get it here: Register (View my Kudos)
Enter 0000000000 to use anonymous mode.
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Horde models not loaded --
Not connected...
Example: http://127.0.0.1:5000/api KoboldCpp works better when you select the Text Completion API and then KoboldCpp as a type!
Connect
Cancel
Not connected...
For privacy reasons, your API key will be hidden after you click 'Connect'.
ClioKayraErato
Connect
Cancel
No connection...
AphroditeDreamGenFeatherlessGeneric (OpenAI-compatible) [LM Studio, LiteLLM, etc.]HuggingFace (Inference Endpoint)InfermaticAIKoboldCppllama.cppMancerOllamaOpenRouterTabbyAPIText Generation WebUI (oobabooga)TogetherAIvLLM
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
Click "Authorize" below or get the key from OpenRouter.
View Remaining Credits
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
Allow fallback providers
Integer (4 bit)Integer (8 bit)Floating point (4 bit)Floating point (6 bit)Floating point (8 bit)Floating point (16 bit)Brain floating point (16 bit)Floating point (32 bit)Unknown
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:5000
oobabooga/text-generation-webuiMake sure you run it with--apiflag
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:5000
For privacy reasons, your API key will be hidden after you click 'Connect'.
A-ZA-ZZ-ADate AscDate DesccategoryTopNewAllAll Classes
-- Connect to the API --
vllm-project/vllm (OpenAI API wrapper mode)
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:8000
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: https://****.endpoints.huggingface.cloud
PygmalionAI/aphrodite-engine (OpenAI API wrapper mode)
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:5000
-- Connect to the API --
ggml-org/llama.cpp (inference server)
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:8080
-- Connect to the API --
Example: http://127.0.0.1:11434
-- Connect to the API -- Download
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:5000
-- Connect to the API -- Experimental feature. Use at your own risk.
inline_model_loading: True must be set in Tabby's config.yml to switch models. Use an admin API key.
Download
For privacy reasons, your API key will be hidden after you click 'Connect'.
Example: http://127.0.0.1:5001
Bypass status checkDerive context size from backend
Connect
Authorize
Cancel
Not connected...
OpenAICustom (OpenAI-compatible)AI21AI/ML APIAzure OpenAIChutesClaudeCloudflare Workers AICohereDeepSeekElectron HubFireworks AIGroqGoogle AI StudioGoogle Vertex AIMistralAIMiniMaxMoonshot AINanoGPTOpenRouterPerplexityPollinationsSiliconFlowxAI (Grok)Z.AI (GLM)
Reverse Proxy
Proxy Presets
Saved addresses and passwords.
Proxy Name
This will show up as your saved preset.
Proxy Server URL
Alternative server URL (leave empty to use the default value).
Doesn't work? Try adding /v1 at the end! /chat/completions suffix will be added automatically.
Proxy Password
Will be used as a password for the proxy instead of API key.
Using a proxy that you're not running yourself is a risk to your data privacy.
ANY support requests will be REFUSED if you are using a proxy.
Do not proceed if you do not agree to this!**
Use "Proxy password" field instead. This input will be ignored.
For privacy reasons, your API key will be hidden after you click 'Connect'.
gpt-5.5gpt-5.5-2026-04-23gpt-5.4gpt-5.4-2026-03-05gpt-5.4-minigpt-5.4-mini-2026-03-17gpt-5.4-nanogpt-5.4-nano-2026-03-17gpt-5.3-chat-latestgpt-5.2gpt-5.2-2025-12-11gpt-5.2-chat-latestgpt-5.1gpt-5.1-2025-11-13gpt-5.1-chat-latestgpt-5gpt-5-2025-08-07gpt-5-chat-latestgpt-5-minigpt-5-mini-2025-08-07gpt-5-nanogpt-5-nano-2025-08-07gpt-4ogpt-4o-2024-11-20gpt-4o-2024-08-06gpt-4o-2024-05-13chatgpt-4o-latestgpt-4o-minigpt-4o-mini-2024-07-18gpt-4.1gpt-4.1-2025-04-14gpt-4.1-minigpt-4.1-mini-2025-04-14gpt-4.1-nanogpt-4.1-nano-2025-04-14o1o1-2024-12-17o1-minio1-mini-2024-09-12o1-previewo1-preview-2024-09-12o3o3-2025-04-16o3-minio3-mini-2025-01-31o4-minio4-mini-2025-04-16gpt-4.5-previewgpt-4.5-preview-2025-02-27gpt-4-turbogpt-4-turbo-2024-04-09gpt-4-turbo-previewgpt-4-0125-preview (2024)gpt-4-1106-preview (2023)gpt-4gpt-4-0613 (2023)gpt-4-0314 (2023)gpt-3.5-turbogpt-3.5-turbo-0125 (2024)gpt-3.5-turbo-1106 (2023)gpt-3.5-turbo-instructbabbage-002davinci-002Bypass API status checkShow "External" models (provided by API)
Get your key from Anthropic's developer console.
For privacy reasons, your API key will be hidden after you click 'Connect'.
claude-opus-4-7claude-opus-4-6claude-opus-4-5claude-opus-4-5-20251101claude-sonnet-4-6claude-sonnet-4-5claude-sonnet-4-5-20250929claude-haiku-4-5claude-haiku-4-5-20251001claude-opus-4-1claude-opus-4-1-20250805claude-opus-4-0claude-opus-4-20250514claude-sonnet-4-0claude-sonnet-4-20250514claude-3-7-sonnet-latestclaude-3-7-sonnet-20250219claude-3-5-sonnet-latestclaude-3-5-sonnet-20241022claude-3-5-sonnet-20240620claude-3-5-haiku-latestclaude-3-5-haiku-20241022claude-3-opus-20240229claude-3-haiku-20240307
Click "Authorize" below or get the key from OpenRouter.
View Remaining Credits
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API -- Allow fallback models
Allow fallback providers To use instruct formatting, switch to OpenRouter under Text Completion API.
Integer (4 bit)Integer (8 bit)Floating point (4 bit)Floating point (6 bit)Floating point (8 bit)Floating point (16 bit)Brain floating point (16 bit)Floating point (32 bit)Unknown
For privacy reasons, your API key will be hidden after you click 'Connect'.
jamba-minijamba-largejamba-1.7-minijamba-1.7-largejamba-1.6-minijamba-1.6-largejamba-1.5-minijamba-1.5-largejamba-instruct-preview
For privacy reasons, your API key will be hidden after you click 'Connect'.
gemini-3.1-pro-previewgemini-3.1-flash-lite-previewgemini-3.1-flash-image-previewgemini-3-pro-previewgemini-3-pro-image-previewgemini-3-flash-previewgemini-2.5-progemini-2.5-pro-preview-06-05gemini-2.5-pro-preview-05-06gemini-2.5-pro-preview-03-25gemini-2.5-flashgemini-2.5-flash-preview-09-2025gemini-2.5-flash-preview-05-20gemini-2.5-flash-litegemini-2.5-flash-lite-preview-09-2025gemini-2.5-flash-lite-preview-06-17gemini-2.5-flash-imagegemini-2.5-flash-image-previewgemini-2.0-pro-exp-02-05 → 2.5-exp-03-25gemini-2.0-pro-exp → 2.5-exp-03-25gemini-exp-1206 → 2.5-exp-03-25gemini-2.0-flash-001gemini-2.0-flash-exp-image-generationgemini-2.0-flash-preview-image-generationgemini-2.0-flash-expgemini-2.0-flashgemini-2.0-flash-thinking-exp-01-21 → 2.5-flash-preview-05-20gemini-2.0-flash-thinking-exp-1219 → 2.5-flash-preview-05-20gemini-2.0-flash-thinking-exp → 2.5-flash-preview-05-20gemini-2.0-flash-lite-001gemini-2.0-flash-lite-preview-02-05gemini-2.0-flash-lite-previewgemini-2.0-flash-litegemma-4-31b-itgemma-4-26b-a4b-itgemma-3n-e4b-itgemma-3n-e2b-itgemma-3-27b-itgemma-3-12b-itgemma-3-4b-itgemma-3-1b-itlearnlm-2.0-flash-experimentalgemini-robotics-er-1.5-preview
Authentication Mode:Express Mode (API Key)Full Version (Service Account)
API Key:
For privacy reasons, your API key will be hidden after you click 'Connect'.
Project ID:
Project ID is only required when selecting regions other than the default (us-central1).
You can find this in a model 404 error message.
Service Account JSON Content:
For privacy reasons, your Service Account JSON content will be hidden after you click 'Validate JSON'.
Validate JSON
Region: globalus-central1us-east1us-east4us-west1us-west2us-west3us-west4europe-west1europe-west2europe-west3europe-west4europe-west6europe-central2asia-northeast1asia-northeast3asia-southeast1asia-south1australia-southeast1
gemini-3.1-pro-previewgemini-3.1-flash-lite-previewgemini-3.1-flash-image-previewgemini-3-pro-previewgemini-3-pro-image-previewgemini-3-flash-previewgemini-2.5-progemini-2.5-flashgemini-2.5-flash-litegemini-2.5-flash-imagegemini-2.5-flash-image-previewgemini-2.0-flash-expgemini-2.0-flash-preview-image-generationgemini-2.0-flashgemini-2.0-flash-001gemini-2.0-flash-lite-001
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
qwen/qwen3-32bdeepseek-r1-distill-llama-70bgemma2-9b-itmeta-llama/llama-4-scout-17b-16e-instructmeta-llama/llama-4-maverick-17b-128e-instructllama-3.1-8b-instantllama-3.3-70b-versatile llama-guard-3-8bllama3-70b-8192llama3-8b-8192mistral-saba-24b
For privacy reasons, your API key will be hidden after you click 'Connect'.
Global (siliconflow.com)China (siliconflow.cn)
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
Global (minimax.io)China (minimaxi.com)
MiniMax-M2.7MiniMax-M2.7-highspeedMiniMax-M2.5MiniMax-M2.5-highspeedMiniMax-M2.1MiniMax-M2.1-highspeedMiniMax-M2M2-her
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
AutoUse pay-as-you-go billing
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
sonarsonar-prosonar-reasoningsonar-reasoning-prosonar-deep-researchr1-1776llama-3.1-sonar-small-128k-onlinellama-3.1-sonar-large-128k-onlinellama-3.1-sonar-huge-128k-onlinellama-3.1-sonar-small-128k-chatllama-3.1-sonar-large-128k-chat
For privacy reasons, your API key will be hidden after you click 'Connect'.
c4ai-aya-23-8bc4ai-aya-23c4ai-aya-expanse-8bc4ai-aya-expanse-32bc4ai-aya-vision-8bc4ai-aya-vision-32bcommand-lightcommandcommand-rcommand-r-pluscommand-r-08-2024command-r-plus-08-2024command-r7b-12-2024command-a-03-2025command-a-vision-07-2025command-light-nightlycommand-nightly
Doesn't work? Try adding /v1 at the end! /chat/completions suffix will be added automatically.
For privacy reasons, your API key will be hidden after you click 'Connect'.
For privacy reasons, your API key will be hidden after you click 'Connect'.
-- Connect to the API --
For privacy reasons, your API key will be hidden after you click 'Connect'.
For privacy reasons, your API key will be hidden after you click 'Connect'.
For privacy reasons, your API key will be hidden after you click 'Connect'.
kimi-k2-0711-previewmoonshot-v1-8kmoonshot-v1-32kmoonshot-v1-128kmoonshot-v1-autokimi-latestmoonshot-v1-8k-vision-previewmoonshot-v1-32k-vision-previewmoonshot-v1-128k-vision-previewkimi-thinking-preview
For privacy reasons, your API key will be hidden after you click 'Connect'.
Common APICoding API
glm-5-turboglm-5v-turboglm-5.1glm-5glm-4.7glm-4.7-flashglm-4.7-flashxglm-4.6glm-4.6vglm-4.6v-flashglm-4.6v-flashxglm-4.5vglm-4.5glm-4.5-airglm-4.5-xglm-4.5-airxglm-4.5-flashglm-4-32b-0414-128kautoglm-phone-multilingual
2025-04-01-preview2024-10-21
For privacy reasons, your API key will be hidden after you click 'Connect'.
Click 'Connect' to fetch model name
The underlying model of your deployment. This is detected automatically when you connect.
Model Sorting
AlphabeticallyPrompt Price (cheapest)Completion Price (cheapest)Context Size
Group by vendors Put OpenAI models in one group, Anthropic models in other group, etc. Can be combined with sorting.
NoneMerge consecutive roles (with tools)Semi-strict (alternating roles; with tools)Strict (user first, alternating roles; with tools)Merge consecutive roles (no tools)Semi-strict (alternating roles; no tools)Strict (user first, alternating roles; no tools)Single user message (no tools)
Connect
Cancel
Additional Parameters
Authorize
Test Message
No connection...
Auto-connect to Last ServerView hidden API keys
Master Import
Master Export
Grayed-out options have no effect when Chat Completion API is used.
Story String
Position:Default (top of context)In-chat @ Depth
Depth:
Role:SystemUserAssistant
Example Separator
Chat Start
Always add character's name to prompt Generate only one line per request Collapse Consecutive Newlines Trim spaces Trim Incomplete Sentences Separators as Stop StringsNames as Stop Strings
Activation Regex
Wrap Sequences with NewlineReplace Macro in SequencesSequences as Stop StringsSkip Example Dialogues Formatting Include Names NeverGroups and Past PersonasAlways
#Story String Sequences
Story String Prefix
Story String Suffix
#User Message Sequences
User Message Prefix
User Message Suffix
#Assistant Message Sequences
Assistant Message Prefix
Assistant Message Suffix
#System Message Sequences
System Message Prefix
System Message Suffix
System same as User #Misc. Sequences
First Assistant Prefix
Last Assistant Prefix
First User Prefix
Last User Prefix
System Instruction Prefix
Stop Sequence
User Filler Message
Prompt Content
Post-History Instructions
JSON serialized array of strings
Replace Macro in Stop Strings
Best match (recommended)None / EstimatedGPT-2Llama 1/2Llama 3Gemma / GeminiJambaQwen2Command-RCommand-ANerdStash (NovelAI Clio)NerdStash v2 (NovelAI Kayra)Mistral V1Mistral NemoYiClaude 1/2DeepSeek V3API (WebUI / koboldcpp)
Token Padding
Auto-Parse Auto-Expand Show Hidden
Add to Prompts Max
Prefix
Suffix
Separator
Bind Model to Templates
Non-markdown strings
Start Reply With
Show reply prefix in chat
Active World(s) for all chats
-- World Info not found --
Global World Info/Lorebook activation settings
Click to expand
Scan Depth
Context %
Budget Cap
Min Activations
Max Depth
Max Recursion Steps
Insertion Strategy Sorted EvenlyCharacter Lore FirstGlobal Lore First
Include Names Recursive Scan Case-sensitive Match Whole Words Use Group Scoring Alert On Overflow
Create or--- Pick to Edit ---
SearchPriorityCustomTitle A-ZTitle Z-ATokens ↗Tokens ↘Depth ↗Depth ↘Order ↗Order ↘UID ↗UID ↘Trigger% ↗Trigger% ↘
Language:DefaultEnglish
Account
Admin Panel
Logout
Avatars:CircleSquareRoundedRectangle
Chat Style:FlatBubblesDocument
Media Style:ListGallery
Notifications:Top LeftTop CenterTop RightBottom LeftBottom CenterBottom Right
Theme Colors
Main Text
Italics Text
Underlined Text
Quote Text
Text Shadow
Chat Background
UI Background
UI Border
User Message
AI Message
Chat Width
Font Scale
Blur Strength
Shadow Width
Reduced MotionNo Blur EffectNo Text ShadowsVisual Novel ModeExpand Message ActionsZen SlidersMad Lab ModeMessage TimerChat TimestampsModel IconsMessage IDsHide Chat AvatarsMessage Token CountCompact Input AreaSwipe # for All MessagesCharacters HotswapAvatar Hover MagnificationTags as FoldersClick to Edit
Char List SubheaderCharacter VersionCreated by
Import Card TagsAskNoneAllExisting Advanced Character SearchPrefer Char. PromptPrefer Char. InstructionsNever resize avatarsAnimated background thumbnailsShow avatar filenamesSpoiler Free Mode
Reload Chat
Debug Menu
Clean-Up
Smooth Streaming Exclude 'Thinking...'
SlowFast
Stream Fade-In
Message Sound Background Sound OnlyRelaxed API URLsLorebook Import DialogAuto-select Input Text Markdown Hotkeys Restore User Input
MovingUI
Reset
MovingUI Preset:
(0 = All)
Streaming FPS
Example Messages Behavior: Gradual push-outAlways include examplesNever include examples
Image Swipe Behavior: Generate newRoll over
Enter to Send: DisabledAutomatic (PC)Enabled "Send" to Continue Quick "Continue" button Quick "Impersonate" button SwipesGestures Auto-load Last ChatAuto-scroll ChatAuto-save Message EditsConfirm message deletionAuto-fix MarkdownForbid External MediaShow {{char}}: in responsesShow {{user}}: in responsesShow <tags> in responsesExperimental Macro EngineRelax message trim in GroupsLog prompts to consoleRequest token probabilitiesShow group chat queuePin greeting message styles
Auto-swipe
EnabledMinimum generated message lengthBlacklisted words Blacklisted word count to swipe
Auto-Continue
Enabled Allow for Chat Completion APIs
Target length (tokens)
AutoComplete Settings
VisibilityDon't showInput length > 1Always show Automatically hide details Show in all macro fields
MatchingStarts withIncludesFuzzy
Style Follow ThemeDarkLight
Keyboard:Select with Tab or EnterSelect with TabSelect with Enter
Font Scale
Width
Parser Flags STRICT_ESCAPING REPLACE_GETVAR
ClassicCoverContainStretchCenter Auto-select New FolderAdd Background
A-ZZ-ANewestOldest
Add to Folder
BackRemove from Folder
Chat backgrounds generated with the Image Generation extension will appear here.
Notify on extension updates Manage extensions
Install extension
Not connected... Auto-connect
Connect
Usage Stats
Backup
Restore
Create
SearchA-ZZ-A
More...Link to Persona Lorebook
Tokens: 0
None (disabled)In Story String / Prompt ManagerTop of Author's NoteBottom of Author's NoteIn-chat @ Depth
Depth:
Role:SystemUserAssistant
Default
Character
Chat
Show notifications on switching personas
Allow multiple persona connections per character
Auto-lock a chosen persona to the chat
PNG
JSON
!User Avatar
Chat
Character
Delete
Cancel
Delete
Cancel
Insert {{original}} into either box to include the respective default prompt from system settings.
Tokens: counting...
Tokens: counting...
Everything here is optional
Tokens: counting...
Tokens: counting...
SystemUserAssistant Tokens: counting...
ShyNormalChatty
Tokens: counting...
Save
Chat History
New Chat
Import Chat
New Folder
A selected World Info will be bound to this character as its own Lorebook.When generating an AI reply, it will be combined with the entries from a global World Info selector.Exporting a character would also export the selected Lorebook file embedded in the JSON data.
--- None ---
Associate one or more auxillary Lorebooks with this character.
NOTE: These choices are optional and won't be preserved on character export!
-- World Info not found --
☰
entries
Comma separated (required) Primary Keywords ⌨️
LogicAND ANYAND ALLNOT ALLNOT ANY
(ignored if empty) Optional Filter ⌨️
Outlet Name
Scan Depth
Case-SensitiveUse globalYesNo
Whole WordsUse globalYesNo
Group ScoringUse globalYesNo
Automation ID
Recursion Level
Content (Tokens:counting...)
Non-recursable Prevent further recursion
Delay until recursion Ignore budget
What this keyword should mean to the AI, sent verbatim
Inclusion Group Prioritize
Group Weight
Sticky
Cooldown
Delay
Filter to Characters or Tags Exclude
-- Characters not found --
Filter to Generation Triggers
NormalContinueImpersonateSwipeRegenerateQuiet
SelectiveUse ProbabilityAdd Memo
Additional Matching Sources
Character Description Character Personality Scenario Persona Description Character's Note Creator's Notes
☰
🔵🟢🔗
Position: ↑Char ↓Char ↑EM ↓EM ↑AN ↓AN @D ⚙️ @D 👤 @D 🤖 ➡️ Outlet
Depth:
Order:
Trigger %:
+++
☰
☰
Prompt List
The list of prompts associated with this marker.
Name A name for this prompt.
RoleSystemUserAI Assistant To whom this message will be attributed.
TriggersNormalContinueImpersonateSwipeRegenerateQuiet Filter to specific generation types.
PositionRelativeIn-chat Relative (to other prompts in prompt manager) or In-chat @ Depth.
Depth 0 = after the last message, 1 = before the last message, etc.
Order Ordered from low/top to high/bottom, and at same order: Assistant, User, System.
Prompt
Forbid Overrides
Source:
${characterName}
Thought for some time
!img1
!img1 !img2
!img1 !img2 !img3
!img1 !img2 !img3 !img4
Language:English SillyTavern is aimed at advanced users.
/help in chat for commands and macros.Import from supported sources or view Sample characters
Before you get started, you must select a persona name.
This can be changed at any time via the `` icon.
!Avatar
in this group
Go back
Add
These will be displayed as swipes on the first message when starting a new chat. Group members can select one of them to initiate the conversation.
Click the button to get started!
Alternate Greeting #
Delete
1/1
Audio
0:00/0:00
Author's Note
Unique to this chat.
Checkpoints inherit the Note from their parent, and can be changed individually after that.
Tokens: 0 Include in World Info Scanning Before Main Prompt / Story StringAfter Main Prompt / Story StringIn-chat @ DepthasSystemUserAssistant
Insertion Frequency(0 = Disable, 1 = Always)
User inputs until next insertion: (disabled)
Character Author's Note (Private) Won't be shared with the character card on export.
Will be automatically added as the author's note for this character. Will be used in groups, but can't be modified when a group chat is open. Tokens: 0 Use character author's note Replace Author's NoteTop of Author's NoteBottom of Author's Note
Default Author's Note
Will be automatically added as the Author's Note for all new chats. Tokens: 0
Before Main Prompt / Story StringAfter Main Prompt / Story StringIn-chat @ DepthasSystemUserAssistant
Insertion Frequency(0 = Disable, 1 = Always)
Chat CFG
Unique to this chat.
Scale1 = disabled
Negative PromptPositive Prompt
Use character CFG scales
Character CFG
Will be automatically added as the CFG for this character.
Scale1 = disabled
Negative PromptPositive Prompt
Global CFG
Will be used as the default CFG options for every chat unless overridden.
Scale1 = disabled
Negative PromptPositive Prompt
CFG Prompt Cascading
Combine positive/negative prompts from other boxes.
For example, ticking the chat, global, and character boxes combine all negative prompts into a comma-separated string.
Always IncludeChat NegativesCharacter NegativesGlobal Negatives
Custom Separator: Insertion Depth:
Token Probabilities
Select a token to see alternatives considered by the AI.
Delete
Cancel
File NameFile Size
Close chat Toggle Panels Author's Note CFG Scale Token Probabilities Back to parent chat Save checkpoint Convert to group
Start new chat Close chat Manage chat files
Delete messages Regenerate Impersonate Continue