Official site · 🇺🇸 United States
| Tier | $/month | Included usage |
|---|---|---|
| Standard | $0.00 | — |
| Professional | $15.00 | — |
| Developer | $150.00 | — |
console only units unstated
As advertised. Standard: pay-as-you-go. Professional: credits refreshing every 24h. Developer: credits refreshing every 8h, ~10% discount past the allowance
What that actually means. Credits are spendable on any model, but the allowance per tier is not stated in tokens, so the plan cannot be priced against metered billing. The refresh cadence is the real differentiator: three times a day on Developer against once on Professional.
Where to check what is left. account dashboard
checked 2026-08-13 · high (official docs) · source
3 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.
| Model | Quant | $/M in | $/M out | Context | Uptime 30m |
|---|---|---|---|---|---|
| DeepSeek V4 Flash | fp8 | $0.15 | $0.32 | 262,100 | 99.8% |
| Qwen3.6 35B A3B | fp8 | $0.19 | $1.19 | 262,140 | 100.0% |
| Qwen3.6 27B | fp8 | $0.39 | $2.89 | 32,768 | 100.0% |