Token pricing
Provider prices. Never a cent more.
Every request routes at the provider’s officially published rate. New models are added to LLM API on their launch day.
GPT-5.2
Claude Opus 4.6
Claude Sonnet 4.6
Gemini 3.0 Pro
Gemini 3.0 Flash
DeepSeek-V3.2
Llama 4 405B
Qwen 3 Max
Mistral Large 3
Grok 4
COMPARE PLANS
Everything, side by side
Models
API keys
Seats
Analytics retention
Zero markup on tokens
Zero data retention
Payment methods
Billing model
Budget & rate limit controls
IAM rules for API keys
Open API usage export
Discounts on LLM usage
Auto fallback routing
Rule-based router
Reserved priority throughput
EvalLab
Prompt management
SAML SSO + SCIM provisioning
RBAC (Role-based access control)
Audit logs (request-level, exportable)
Data export to data lakes / SIEM
Compliance & agreements
Custom model deployments
BYOK (Bring Your Own Key)
On-prem / VPC / private cloud
Model hosting region (EU, US, APAC)
AWS, Azure & Google Cloud Marketplace
Dedicated CSM, Slack channel & priority support
Onboarding & migration assistance
Custom SLA & contract
Approval is a checkbox, not a project.
Built to the standards your security, legal, and compliance teams already trust.
SOC 2 Type II
ISO 27001
CCPA Compliant
GDPR Compliant
FAQ
Frequently Asked Questions
How does Startup pricing work?
Pure pay-as-you-go with a prepayment option. Zero platform fees, zero markup on tokens, unlimited seats, unlimited API keys. You only pay for inferences at the exact official rate charged by the model providers.
Is my data stored or used for training?
No. By default, we store metadata only: which API key was used, which model was called, timestamp, and token counts. We do not store your prompts or responses. Your data is never used for training, model improvement, or any other purpose beyond serving your request.
Can I select the server region for my requests?
Yes. We support multiple regional options including EU, US, and Asia Pacific. You can choose your region when you create an API key, and different keys can use different regions. This is especially important if you’re handling sensitive data, need to comply with data residency requirements, or want to optimize for latency in specific geographies.
How do the discounts on LLM usage work?
At enterprise scale, we negotiate volume-based rates directly with model providers and pass the savings through to you. The exact discount depends on your committed volume, model mix, and contract term. Typical deals offer 5% to 30% off published token prices. But sometimes it could be up to 80% discount.
Do you have any API rate limits?
New users start with 60 requests per 60 seconds. If you need higher limits, contact us via chatbot or support@llmapi.ai for a quick increase — there’s no hard ceiling.
What’s included in “Compliance & agreements”?
We are SOC 2 Type II certified, ISO 27001 certified, and GDPR and CCPA compliant. We provide the documentation and compliance evidence you need for regulated industries.
Start in one line of code.
Swap your API key. Keep your code.
No credit card required