Bring Your Own Keys (BYOK)
Bring Your Own Keys (BYOK) allows you to connect your own API keys from providers like OpenAI, Anthropic, Google, and others to Adaptive. This gives you maximum cost savings while still benefiting from Adaptive’s intelligent routing, caching, and reliability features.How BYOK Works
When you provide your own provider API keys, Adaptive uses them to make requests on your behalf instead of using our pooled API keys. This means:Pay Only Overhead
You only pay Adaptive’s overhead fee, not the underlying model costs. Your provider bills you directly for the model usage.
Full Routing Control
Continue to benefit from intelligent routing, semantic caching, fallback mechanisms, and all other Adaptive features.
Enhanced Privacy
Your API requests go through your own provider accounts, giving you complete control and isolation.
Usage Tracking
Track usage across both Adaptive’s dashboard and your provider dashboards for comprehensive visibility.
Pricing with BYOK
Overhead-Only Pricing
When using your own API keys, you only pay Adaptive’s overhead:- Input tokens: $0.10 per 1M tokens
- Output tokens: $0.20 per 1M tokens
- Semantic cache hits: 50% off (half the normal overhead)
- Prompt cache hits: Free
Cost Example
Let’s say you make a request that uses:- 100,000 input tokens
- 50,000 output tokens
- Provider model cost (e.g., GPT-4): ~3.75 (output) = $5.00
- Adaptive overhead: 0.01 (output) = $0.02
- Total charged by Adaptive: $5.02
- Provider model cost: ~$5.00 (billed directly by OpenAI to you)
- Adaptive overhead: 0.01 (output) = $0.02
- Total charged by Adaptive: $0.02
- Total charged by OpenAI: $5.00
Benefits of BYOK
Maximum Cost Savings
By paying only the overhead fee to Adaptive, you can save significantly on high-volume workloads. This is especially valuable for:- High-traffic production applications
- Large-scale batch processing
- Development and testing environments
- Cost-sensitive projects
Complete Control
When you use your own keys:- Billing control: Direct relationship with providers for billing and invoicing
- Usage limits: Set your own rate limits and spending caps at the provider level
- Account isolation: Separate environments for dev, staging, and production
- Compliance: Meet specific compliance requirements that require direct provider relationships
Privacy and Data Governance
- Your requests are authenticated with your own credentials
- No request pooling with other Adaptive users
- Direct audit trail with your provider
- Easier compliance with data residency requirements
Setting Up BYOK
1
Get Provider API Keys
Obtain API keys from the providers you want to use:
2
Add Keys to Adaptive
In your Adaptive dashboard:
- Navigate to your project settings
- Go to “Custom API Keys” or “Provider Configurations”
- Add your provider API keys securely
- Keys are encrypted and stored securely
3
Enable BYOK for Project
Configure your project to use custom keys:
- Set priority for which providers to use
- Configure fallback behavior
- Test the configuration with sample requests
4
Monitor Usage
Track your usage across both:
- Adaptive dashboard (overhead costs, routing decisions)
- Provider dashboards (model costs, quotas)
Supported Providers
BYOK is currently supported for:OpenAI
GPT-4, GPT-3.5, and all OpenAI models
Anthropic
Claude Opus, Sonnet, and Haiku
Gemini Pro, Flash, and other models
Groq
All Groq-hosted models
DeepSeek
DeepSeek models and variants
More Coming
Additional providers being added regularly
Security and Best Practices
Key Security
Never share your API keys or commit them to version control. Adaptive stores your keys encrypted at rest and in transit.
- Rotate keys regularly
- Use separate keys for dev/staging/production
- Monitor key usage in both Adaptive and provider dashboards
- Set spending limits at the provider level
- Revoke unused or compromised keys immediately
Monitoring and Alerts
Set up monitoring for:- Unexpected usage spikes
- Provider quota exhaustion
- Failed authentication attempts
- Cost threshold alerts
Routing with Custom Keys
Even with BYOK enabled, Adaptive’s intelligent routing continues to work:- Model Selection: Adaptive analyzes your request complexity
- Provider Selection: Routes to the optimal provider based on:
- Your available custom keys
- Model capabilities and performance
- Current provider availability
- Cost optimization
- Fallback: If your custom key fails or hits quota, Adaptive can:
- Fall back to other custom keys you’ve configured
- Fall back to Adaptive’s pooled keys (at standard pricing)
- Return graceful errors based on your configuration
Frequently Asked Questions
Do I need custom keys for all providers?
Do I need custom keys for all providers?
No, you can mix and match. Use custom keys for some providers and let Adaptive use its pooled keys for others. Adaptive will route intelligently based on what’s available and most cost-effective.
What happens if my custom key reaches its quota?
What happens if my custom key reaches its quota?
Adaptive can automatically fall back to other configured keys or its own pooled keys, depending on your fallback configuration. You can also configure strict mode to fail the request instead.
Can I see which key was used for each request?
Can I see which key was used for each request?
Yes, Adaptive’s dashboard shows detailed request logs including which provider and which key (yours vs pooled) was used for each request.
Is BYOK available on all plans?
Is BYOK available on all plans?
BYOK is available on Team and Enterprise plans. Developer plan users can upgrade to access this feature.
Getting Started
Ready to set up BYOK?Configure Custom API Keys
Go to your project settings to add your provider API keys and start saving on overhead costs



