Barrack API Documentation
AI Chat
Copy Page
Barrack API Documentation
Platform Documentation
Getting Started
Authentication & Access
Account Management
API Keys
GPU Models
Regions
Instance
OS Images
Bootsource Management
Deploy Instance
Instance Management
Hibernation
View Instances
SSH Keys
Add SSH Keys
Manage SSH Keys
Volumes
Overview
Create Volume
List and View Volumes
Attach Volumes
Detach Volumes
Clone Volumes
Resize Volume
Delete Volume
Advanced Configurations
Network And Security
Cloudinit Script
Startup Script
Firewall
Manage Firewall
Rules and Attachment
Snapshot
Overview
Manage Snapshots
Restore Snapshots
Custom Images
Overview
Create and Manage Images
dashboard
"Dashboard Overview"
"VM Management"
AI Chat
AI Chat
Balance
Get credit balance
GET
GPU Stocks
Get GPU stock availability
GET
GPU Specs
Get GPU specifications
GET
Regions
List available regions
GET
Pricing
Get pricing information
GET
Get pricing information
POST
Deploy Instance
Create a new instance
POST
Instance management
List instances
Get instance details
Get instance billing
Start instance
Stop instance
Reboot instance
Hibernate instance
Restore hibernated instance
Toggle public IP for instance
Add instance security rule
Remove instance security rule
Delete instance
OS Images
List OS images
SSH Keys
List SSH keys
Get SSH key
Create SSH key
Delete SSH key
Volumes
List volumes
Create volume
Get volume details
Delete volume
Resize volume
Clone volume
Attach volumes to instance
Detach volumes from instance
List available volume types
Get volume billing
Firewalls
List firewalls
Get firewall details
Get supported protocols
Get firewalls attached to instance
List instances available for firewall attachment
Create firewall
Delete firewall
Add firewall rule
Remove firewall rule
Attach firewall to instances
Scripts
List all startup scripts
Get startup script details
Create a startup script
Update a startup script
Delete a startup script
Delete multiple startup scripts
Snapshots
List snapshots
Get snapshot details
List Instance eligible for snapshot creation
Get snapshot billing
Create snapshot
Delete snapshot
Restore snapshot
Images
List custom images
Get image details
Create image from snapshot
Delete custom image
Get snapshot-image relationship
Get snapshot-image relationship list
AI Chat
Get available AI models
Chat with AI
Get AI usage summary
Get AI usage history
Schemas
AITransaction
AddFirewallRuleRequest
AddFirewallRuleResponse
AddVMSecurityRuleResponse
AttachFirewallRequest
AggregatedBillingResponse
AttachFirewallResponse
AttachVolumesRequest
AttachVolumesResponse
AttachedFirewall
BatchSnapshotImageRelationshipResponse
Balance
Billing
ChatCompletionsRequest
ChatCompletionsResponse
CloneVolumeRequest
BillingRecord
CloneVolumeResponse
BillingSummary
CreateFirewallRequest
CreateFirewallResponse
CreateImageFromSnapshotRequest
CreateSSHKeyRequest
CreateScriptRequest
CreateSnapshotRequest
CreateSnapshotResponse
CreateSSHKeyResponse
CurrencyEnum
Data
CreditBalanceResponse
DeleteFirewallResponse
CreateVolumeRequest
DeleteSnapshotResponse
CreateVolumeResponse
DeleteVMResponse
DetachVolumesRequest
DetachVolumesResponse
DeploymentRequest
DirectionEnum
DeploymentResponse
EthertypeEnum
ErrorResponse
FirewallAttachment
DeleteVolumeResponse
DeleteSSHKeyResponse
FirewallEnvironment
FirewallResponse
FirewallRule
FirewallVM
GetBatchSnapshotImageRelationshipsRequest
GetFirewallDetailsResponse
GPUStockConfiguration
GPUSpec
GetHibernatedVMsResponse
GPUStockItem
GPUSpecsResponse
GetSupportedProtocolsResponse
GPUStocksResponse
GetVMAttachedFirewallsResponse
GetVolumeTypesResponse
HibernateVMResponse
HibernationBillingMetrics
ListFirewallsResponse
ListUserVMsResponse
ListVMsResponse
ModelsResponse
GetSSHKeysResponse
Pagination
PricingRequest
OSImage
PricingResponse
OSImagesResponse
Protocol
GpuCountEnum
ProtocolEnum
Image
GpuModelEnum
GetVolumeDetailsResponse
RebootVMResponse
ImageCreateResponse
RecentHibernation
ImageDeleteResponse
GetVolumesWithNextNameResponse
RemoveFirewallRuleResponse
ImageDetailResponse
RemoveVMSecurityRuleResponse
Region
ImageListResponse
ResizeVolumeRequest
RegionsResponse
Price
ResizeVolumeResponse
ResourceTypeEnum
RestoreSnapshotRequest
RestoreSnapshotResponse
RestoreVMResponse
Snapshot
SnapshotImageRelationshipResponse
Specs
StartVMResponse
StopVMResponse
TierEnum
UpdateScriptRequest
UsageHistoryResponse
UsageSummaryResponse
RegionEnum
UserVM
VMDetailsResponse
VMFlavor
VMImage
VMInstance
VMResponse
SpecsMetadata
VMSecurityRule
VMSecurityRuleRequest
VMStatus
VMVolumeAttachment
Script
VolumeTypeEnum
SSHKeyResponse
ScriptListResponse
ToggleVMPublicIPResponse
VolumeBillingRecord
VolumeBillingSummary
VolumeHourlyBillingResponse
VolumeResponse
AI Chat
Copy Page
AI Chat
AI Chat
#
Interactive chat interface for text generation, conversation, and analysis using large language models.
Accessing AI Chat
#
Navigate to
barrack.ai/ai-chat
Available Model
#
gpt-oss-120b
General purpose language model
Context window: 131,072 tokens
Pricing: 0.45 USD/EUR per 1M tokens, 45 INR per 1M tokens
Supports real-time streaming responses
Using the Chat Interface
#
Sending Messages
#
1
Type Your Message
Enter your message in the text field at the bottom
2
Send
Press Enter to send
Click Send button
Use Shift+Enter for new lines
3
Receive Response
Response streams in real-time as the model generates text
Message Features
#
Copy Messages:
Click the copy button on assistant responses to copy to clipboard
Token Usage:
Each response shows token count and progress bar (displayed as used/8,192 per message)
Clear Chat:
Remove all messages using "Clear Chat" in settings
Chat Settings
#
Click the Settings icon to configure chat parameters.
Settings save automatically as you change them.
AI Assistant Type
#
Default Assistant:
Standard helpful assistant behavior
Custom Instructions:
Define specific behavior, expertise, or response style in the text field
Generation Parameters
#
Temperature (0.0 - 2.0)
Max Tokens (1 - 4,095)
Top-P (0.0 - 1.0)
Top-K (-1 to 200)
Presence Penalty (-2.0 to 2.0)
Repetition Penalty (-2.0 to 2.0)
Cost and Billing
#
Pricing
#
Currency
Price per 1M Tokens
USD
$0.45
EUR
€0.45
INR
₹45
Billing:
Charges deduct from account balance after each request completes
Token Estimation:
1 token ≈ 4 characters, 1,000 words ≈ 1,300 tokens
Rate Limits
#
60 requests per minute
per account
Common Errors
#
Insufficient Credits
Rate Limit Exceeded
Context Length Exceeded
Model Not Available
Invalid Parameters
Profile Incomplete
Support
#
For technical assistance, contact:
[email protected]
Include in your message:
Account email
Error codes or messages
Steps to reproduce issue
Previous
"VM Management"
Next
Get credit balance