Pricing
Pay for the
tokens you use.
Every request is metered to the token. We charge the provider's per-million rate plus 25% — and we show you both numbers, every time. No subscriptions. No seat fees. No minimum.
Top up
Buy credits to fund your account ($1 = 1 credit)
Make requests
Each call charged: tokens × provider rate × 1.25
See the cost
Real provider cost + our margin, on every response
≈ 4.0M Opus 4.7 input
≈ 40.0M Opus 4.7 input
≈ 160.0M Opus 4.7 input
Same per-token rate regardless of pack size. The packs are just top-up amounts — your real cost is per-call. Credits never expire.
Per model
What does $25 get you?
All prices below include our 25% margin. The "$25 buys" column shows input tokens you can send for $25 at that model's rate.
| Model | In $/M | $25 buys |
|---|---|---|
| Claude Opus 4.7 1M context flagship | $6.25 | 4.0M |
| Claude Sonnet 4.6 200K context flagship | $3.75 | 6.7M |
| Claude Haiku 4.5 200K context | $1.25 | 20.0M |
| GPT-5.5 1M context | $6.25 | 4.0M |
| GPT-5.4 1M context | $3.13 | 8.0M |
| GPT-5.4 Mini 400K context | $0.940 | 26.6M |
| Gemini 3.1 Pro Preview 1M context | $2.50 | 10.0M |
| Gemini 3 Flash Preview 1M context value | $0.625 | 40.0M |
| Grok 4.20 Reasoning 2M context | $2.50 | 10.0M |
| Grok 4.1 Fast 2M context | $0.250 | 100.0M |
| DeepSeek V4 Pro 1M context value | $2.18 | 11.5M |
| DeepSeek V4 Flash 1M context value | $0.175 | 142.9M |
Cost = (input tokens × in $/M) + (output tokens × out $/M). Output tokens are typically 2–6× more expensive than input on most providers.
Plus image, video, voice, and TTS models priced per asset. Full table in the docs.
Ready to build?
Sign up, get free starter credits, and see the real per-call cost on your first response.
FAQ
Frequently asked questions
How am I actually charged?
Per request, per token. Every API call is metered: input tokens × the per-million input rate, output tokens × the per-million output rate. We charge the provider rate plus 25%. The exact cost shows in the response headers and on every entry in your dashboard. No rounding up, no per-task fudge factors.
Why credits then?
Credits are just a top-up balance — $1 = 1 credit. Your balance ticks down as actual API costs accrue. Nothing more clever than that. We don't pretend a 'credit' equals a fixed amount of compute, because it doesn't — different models cost wildly different amounts per token.
Do credits expire?
No. Your money is your money. Use it whenever.
Can I choose which model runs each call?
Yes. Pick your model per call, per mission, per task. Mix providers — Opus 4.7 for planning, Sonnet 4.6 for execution, V4 Flash for cheap throwaway calls. Your call. We just route the request and bill you the real cost plus margin.
What happens if I run out of credits mid-mission?
The mission pauses. Top up and resume exactly where you left off. No work lost, no restarts.
Why the 25% margin?
Because the orchestration engine, multi-provider routing, sessions, billing, observability, and the live workspace aren't free to build or run. Every API response shows the raw provider cost and our margin separately — no obfuscation. If you're a heavy user (>$50/mo) you can apply for the Developer tier (12.5%) or Lifetime (0%). See the developers page.
Do I need a credit card to try it?
No. Sign up, get free starter credits. Top up only when you want to keep going.