Fireworks AI Docs home page
Search...
⌘K
Ask AI
Community
Status
Dashboard
Dashboard
Search...
Navigation
Data security
Documentation
SDKs
CLI
API Reference
Model Library
FAQ
Changelog
Account & Access
Company account access
Close account
Multiple accounts login
GitHub authentication email
LinkedIn authentication email
Billing & Pricing
Pricing structure
Fine-tuned model fees
Bulk usage discounts
Serverless discounts
Credits & billing system
Account suspension reasons
$1 credit depleted
Missing credits issue
Invoice vs credits
Credit receipts
Models API billing
Serverless prompt caching billing
Input image pricing
Deployment & Infrastructure
Performance optimization
Performance benchmarking
Model latency ranges
Performance factors
Performance best practices
Serverless latency guarantees
Serverless SLAs
Serverless quotas
Fine-tuned serverless costs
Model removal notice
Serverless timeout issues
System scaling
Auto scaling support
Throughput capacity
Request handling factors
Autoscaling cost impact
On-demand rate limits
On-demand billing
GPU deployment billing
GPU selection guide
Custom model deployment issues
Deployment performance expectations
Performance consultation
Single replica optimization
Models & Inference
Custom base models
Serverless model availability
Model availability requests
Llama 3.1 405B quantization
API batching & load balancing
Request handling capacity
Safety filter controls
Token limit controls
Streaming performance metrics
FLUX multiple images
FLUX image-to-image
FLUX custom LoRA
SDXL ControlNet sizing
Fine-tuning
Fine-tuning service
Fine-tuning model support
Fine-tuned model access
firectl invalid ID errors
Llama 3.1 LoRA deployment
Security & Compliance
Data encryption at rest
Data encryption in transit
Client-side encryption options
Security policy documentation
LLM model guardrails
Private network connections
Security certifications
Support & General
General support
Performance support
Deployment regions
Support options
Support process
Enterprise support
Enterprise support Slack
Enterprise support tiers & SLAs
Enterprise tier quotas
On this page
Data at rest
Data in transit
Encryption options
Additional information
Data security
Copy page
Information about Fireworks.ai data encryption and security measures.
Copy page
Data at rest
Q: How is data encrypted at rest?
All resources stored within Fireworks are
encrypted at rest
, including:
Models
Datasets
LoRA Adapters
Other stored resources
Data in transit
Q: How is data encrypted in transit?
All data passed through Fireworks is encrypted using
industry-standard protocols and methods
.
Encryption options
Q: Does Fireworks provide client-side encryption or allow customers to bring their own encryption keys?
Currently, Fireworks does not provide:
Client-side encryption
Customer-managed keys
for encrypting data at rest
Note
: We continuously evaluate additional encryption options based on customer needs and security requirements.
Additional information
If you experience any issues during these processes, you can:
Contact support through Discord at
discord.gg/fireworks-ai
Reach out to your account representative (Enterprise customers)
Email
[email protected]
Was this page helpful?
Yes
No
Assistant
Responses are generated using AI and may contain mistakes.