Pricing

Simple, transparent pricing

Start for free. Scale as you grow. All model costs included.

Free

$0

Perfect for experimentation

No credit card required
  • 1 project
  • 2 agents
  • 5 agent invocations/day
  • Apps and MCP connectors
  • 10 requests/minute
  • Hikigai-hosted personal workspace
  • Python & Node SDKs
  • Customer cloud (BYOC)
  • Team organization
Get Started Free
Most Popular

Pro

Admin

Hosted personal workspace, granted by Hikigai admin

  • 5 projects
  • 10 agents
  • 50 agent invocations/day
  • 2 apps and 2 MCP connectors
  • 100 requests/minute
  • Hikigai-hosted personal workspace
  • Python & Node SDKs
  • Customer cloud (BYOC)
  • Team organization
Ask an admin

Enterprise

BYOC

Team organization on your own cloud

  • Unlimited projects, agents, apps, MCP
  • Unlimited agent invocations (rpm/rpd still apply)
  • 200 requests/minute
  • 10,000 API requests/day
  • Customer cloud required to deploy
  • Shared org quota for every member
  • Python & Node SDKs
  • SSO / SAML
  • Dedicated support
Create an organization
SOC2 Compliant
Enterprise Security
Powered by AWS

Compare plans in detail

FeatureFreeProEnterprise
WorkspacePersonal (hosted)Personal (hosted)Team org (your cloud)
Projects15Unlimited
Deployed agents210Unlimited
Agent invocations/day550Unlimited
Apps02Unlimited
MCP connectors02Unlimited
API requests/day203,00010,000
Requests/minute10100200
SDK scopesinvokedeploy, invoke, manageAll + admin
Models includedAllAllAll + Custom
Streaming responses
Session memory
Analytics retention7 days90 daysUnlimited
SupportCommunityEmail (24h)24/7 Dedicated
SLA—99.9%99.99%

Works with your code

Same SDK, any plan

Your code doesn't change when you upgrade. The SDK automatically uses your plan's rate limits and scopes.

  • API key contains your plan info
  • Rate limit headers in every response
  • Usage tracking via SDK
from hikigai import Hikigai

client = Hikigai()  # Uses HIKIGAI_API_KEY

# Check your usage
usage = client.usage()
print(f"Used: {usage.invocations_used}")
print(f"Remaining: {usage.invocations_limit}")

# Rate limit info in response
response = agent.invoke("Hello")
# Response headers:
# X-RateLimit-Limit: 100
# X-RateLimit-Remaining: 95
# X-RateLimit-Reset: 1704153600

Frequently Asked Questions

What counts as an invocation?

Each time you call agent.invoke() or POST /agents/{id}/invoke counts as one invocation, regardless of response length or tokens used.

What are scopes?

Scopes control what your API key can do. "invoke" lets you use agents. "deploy" lets you create agents. "manage" lets you update/delete agents.

Can I upgrade or downgrade at any time?

Yes, you can change your plan at any time. Upgrades take effect immediately. Downgrades take effect at the next billing cycle.

Do you charge for model tokens?

No! Your Hikigai plan includes all infrastructure costs. Model tokens (Claude, Llama, etc.) are included in your plan pricing.

What happens if I exceed my rate limit?

You'll receive a 429 error with a Retry-After header. The SDK automatically handles retries with exponential backoff.

Is there a free trial for Pro?

Yes, Pro comes with a 14-day free trial. No credit card required to start.

Ready to get started?

Deploy your first agent in minutes. Free forever to start.