Pricing

Plans

Each model is billed at its own price per million input and output tokens (GET /v1/models/pricing), and every plan pays that same price. A subscription changes what your key can reach and how fast, not what a token costs.

What you get
Pro$19.99/mo
Premium$100.00/mo
Endpoints
Agent and swarm completions
The standard endpoints, on every plan.
Graph workflows
/v1/graph-workflow/completions
Agent batch
/v1/agent/batch/completions
Swarm batch
/v1/swarm/batch/completions
Reasoning agents
/v1/reasoning-agent/completions
Batched grid workflows
/v1/batched-grid-workflow/completions
Models
Full model catalogue
Every model the platform lists, each at its own token price.
Premium models
GPT-5.6, Claude Opus 5, Gemini 3.1 Pro
Throughput and support
Rate limits
Requests per minute, and concurrent runs.
BaseHigherHighest
Compute lane
StandardPriorityPriority
Execution history
How far back History and GET /v1/account/logs reach.
50 newest, last 7 days5,000 newest, last 90 daysFull history
Support
CommunityCommunity24/7 priority
Billing
Token rate
Each model has its own price, the same on every plan.
SameSameSame
Credit on sign-up
$5.00$5.00$5.00
Balance floor for premium endpoints
Below this, a premium call is refused before any work runs.
—$1.00$1.00
Monthly price
$0.00$19.99$100.00

New accounts start with $5.00 of credit on every plan. Usage is drawn from your balance; a subscription is billed separately from what you spend on tokens.

The premium endpoints

Five endpoints are subscriber-only. On a free key each answers 403 with an upgrade link rather than running, so nothing is charged for a request that was never going to work.

Graph workflows

POST /v1/graph-workflow/completions

Directed agent nodes and edges, compiled and run with parallel execution where the graph allows it. The backing endpoint for the Workflow Builder.

Agent batch

POST /v1/agent/batch/completions

Hundreds of agent tasks in parallel in one request, for document analysis and other work that is wide rather than deep.

Swarm batch

POST /v1/swarm/batch/completions

The same, for whole swarms: many collaborative runs executed concurrently instead of one after another.

Reasoning agents

POST /v1/reasoning-agent/completions

Self-consistency, majority voting and iterative refinement, for answers that need to be right more than they need to be fast.

Batched grid workflows

POST /v1/batched-grid-workflow/completions

Every task against every agent as a matrix, for comparing approaches side by side. The backing endpoint for the Grid.

Usage rates

Charged on top of token usage, and identical on every plan.

Agent
Per agent, on swarm and workflow endpoints.
$0.01
Image
$0.02
Exa search
$0.04
Night discount
Off token cost on swarm completions, overnight.
−50%
Estimate a workload