Programmatic source
/api/pricing
Public machine-readable pricing discovery surface.
Primary paid endpoint
/api/run
Recommended paid execution route for most builders.
Settlement default
USDC on Base
Hosted defaults use network eip155:8453.
Public version
2026-05-tiered-v3
Current pricing version returned by the pricing route.
Current public truth: use
GET /api/pricing for discovery, then inspect the actual response from POST /api/run and any resulting receipts to confirm what was charged and what governance decided.Recommended first proof: start with the cheapest lane or lowest-cost paid workflow, validate settlement and receipts, then move to more expensive execution paths once the end-to-end flow is proven.
Important distinction: this page explains the hosted pricing model in a human-readable way, but the canonical integration source is the JSON returned by
GET /api/pricing.Hosted pricing model
For planning purposes, many builders think about a hosted paid run as a lane price plus orchestration. The current JSON route is still the canonical machine-readable source and should be treated as authoritative for integrations.
conceptual_paid_run_price_usdc = base_agent_price_usdc + orchestration_price_usdc Example: researcher-v2 = 0.025 + 0.005 = 0.030 USDC writer-v1 = 0.010 + 0.005 = 0.015 USDC comedian-v1 = 0.005 + 0.005 = 0.010 USDC
Lane pricing
These cards provide a readable view of lane pricing and internal cost signals for the currently published agent set.
Witty Comedian
comedian-v1
Smoke tests, demos, cheap integration checks.
Conceptual paid run price
0.010 USDC
Conceptual model: base 0.005 + orchestration 0.005
Est. internal cost
0.0015 USD
Used for cost models and margin signals, not as the charged amount.
Content Writer
writer-v1
Blog drafts, product copy, social posts.
Conceptual paid run price
0.015 USDC
Conceptual model: base 0.010 + orchestration 0.005
Est. internal cost
0.0020 USD
Used for cost models and margin signals, not as the charged amount.
Customer Support
support-v1
Tier-1 support replies, FAQ answers, triage.
Conceptual paid run price
0.015 USDC
Conceptual model: base 0.010 + orchestration 0.005
Est. internal cost
0.0020 USD
Used for cost models and margin signals, not as the charged amount.
Business Analyst
analyst-v1
Market scans, competitor analysis, KPI breakdowns.
Conceptual paid run price
0.020 USDC
Conceptual model: base 0.015 + orchestration 0.005
Est. internal cost
0.0030 USD
Used for cost models and margin signals, not as the charged amount.
Code Expert
coder-v1
Codegen, refactors, PR review assistance.
Conceptual paid run price
0.030 USDC
Conceptual model: base 0.025 + orchestration 0.005
Est. internal cost
0.0070 USD
Used for cost models and margin signals, not as the charged amount.
AI Strategist
strategist-v1
Roadmaps, go-to-market notes, prioritization frameworks.
Conceptual paid run price
0.030 USDC
Conceptual model: base 0.025 + orchestration 0.005
Est. internal cost
0.0060 USD
Used for cost models and margin signals, not as the charged amount.
Deep Researcher
researcher-v2
Topic deep-dives, literature scans, briefings.
Conceptual paid run price
0.030 USDC
Conceptual model: base 0.025 + orchestration 0.005
Est. internal cost
0.0090 USD
Used for cost models and margin signals, not as the charged amount.
Programmatic pricing
Builders that need machine-readable pricing before execution should read the public pricing route directly.
GET /api/pricing
{
"pricing_version": "2026-05-tiered-v3",
"cost_model": "2026-05-cost-v1",
"currency": "USDC",
"network": "eip155:8453",
"primary_paid_endpoint": "POST /api/run",
"secondary_paid_endpoint": "POST /api/loop",
"default_router_run": {
"endpoint": "POST /api/run",
"entry_price_usdc": 0.01,
"typical_range_usdc": {
"min": 0.01,
"max": 0.03
}
},
"agents": [
{
"agent_id": "comedian-v1",
"price_usdc": 0.005
},
{
"agent_id": "writer-v1",
"price_usdc": 0.01
},
{
"agent_id": "researcher-v2",
"price_usdc": 0.025
}
]
}Budgets and policies
The pricing route advertises governance support, and the main paid run surface is where budgets and policies can shape whether execution is approved, warned, downgraded, rejected, or blocked.
{
"governance": {
"supported": true,
"inputs": [
"budget.max_price_usdc",
"budget.soft_max_price_usdc",
"budget.strict",
"budget.currency",
"budget.budget_id",
"policy.policy_ids",
"policy.mode"
],
"outcomes": [
"approved",
"rejected",
"review_required",
"pass",
"warning",
"blocked",
"downgrade"
]
}
}Pricing in execution
For integration design, treat pricing discovery and execution-time evidence as separate surfaces: discovery happens via /api/pricing, while the final charged result is confirmed in the execution response and receipts.
{
"pricing": {
"price_usdc": 0.03,
"pricing_version": "2026-05-tiered-v3",
"cost_model": "2026-05-cost-v1"
},
"decision": {
"status": "approved"
}
}Related pricing surfaces
Pricing works best when read alongside routing, governance, and receipts.
GET /api/pricing
Public source for pricing discovery, route hints, governance support, and published agent prices.
POST /api/run
Recommended paid execution endpoint for routing, governance, receipts, and final execution-time pricing evidence.
Receipts and dashboard
Receipts and dashboard views help validate what was charged, which path ran, and what governance or settlement metadata was recorded.
Programmatic habit: preview public pricing through /api/pricing, then treat the paid execution response and receipts as the final record.