Pricing for APIs and agents.
Start with the same live prediction-market surface across HTTP, CLI, SDK, MCP, and Agent SDK. Upgrade when you need more request headroom, more SF-paid model budget, or support for production workflows.
Explore the live read surface before you attach billing.
- rpm
- 60
- req/mo
- 1K
- sf tokens
- 100K
- · Live market and search reads
- · CLI, SDK, MCP, and Agent SDK access
- · Starter SF-token budget for SF-paid LLM calls
For small products, personal agents, and real API traffic.
- rpm
- 300
- req/mo
- 50K
- sf tokens
- 2M
- · Small apps, scripts, and personal agents
- · More request headroom for real traffic
- · Stripe billing with email support
For production agents, scheduled jobs, and heavier LLM use.
- rpm
- 1,000
- req/mo
- 500K
- sf tokens
- 20M
- · Production agents and scheduled research jobs
- · Higher burst headroom and SF-token budget
- · Priority support for integration issues
For desks that need private data, custom limits, or support SLAs.
- rpm
- —
- req/mo
- —
- sf tokens
- —
- · Custom RPM, refresh, and monthly ceilings
- · Private feeds or integration work
- · Contracted support and security review
What the meter counts.
The same limits show in dashboard billing. Admin tier changes hot-reload from the tier config, so the numbers on this page are the contract the API enforces.
Burst ceiling for authenticated traffic. When you hit it, the API returns 429 with Retry-After instead of silently queueing work.
Raw request count. LLM endpoints do not get a hidden request multiplier; SF-paid model compute is metered separately.
One SF token equals one micro-dollar of LLM compute SimpleFunctions paid for. BYOK model calls through the SDK do not spend this budget.
FAQ.
What happens at the wall?
429 with an X-SF-Upgrade-Url header. Block reasons: rpm, hard_cap, or sf_tokens. Upgrading raises the limits; existing monthly counters do not reset.
Can I bring my own model key?
Yes. BYOK paths through the SDK route model spend to your provider account. They do not spend SF tokens. Only model calls paid by SimpleFunctions consume the SF-token budget.
Does MCP count differently?
MCP tools that hit SF endpoints count against your monthly requests. Tools that hit Kalshi or Polymarket directly don't — we're not in the path, so we don't meter. Authenticate the MCP server with your sf_live_* key.
How is an SF token defined?
One SF token equals one micro-dollar ($0.000001) of LLM compute. We read OpenRouter's reported usage.total_cost for the call, multiply by 1M, and that is your SF-token charge. When a provider does not return cost, we estimate from the server-side model pricing table and keep the request in your audit trail.
Can I downgrade later?
Yes. Use the Stripe Customer Portal from your dashboard. Downgrade takes effect at the end of the current billing period.
Do crawlers consume my quota?
No. Recognized crawler traffic is separated from user quota. Your plan is metered on authenticated usage and user-scoped API keys.
Custom pipelines.
If the self-serve plans are too rigid, we can tune limits, refresh cadence, private data feeds, routing, and integration shape around your workflow.
For quant research desks, market makers, and prop teams operating at scale.
Talk to the team →