Text: unlimited within your plan
Chat and embeddings calls are not billed per token. Control is by requests per minute (fair use) — each plan has its own limit. Use it freely within that limit.
A subscription with clear quotas and no surprise costs. Text is unlimited within your plan (controlled by requests/min, fair use); images come with an included monthly quota and overage billed per image. All amounts are always in US dollars (USD).
| Plan | USD/month | Models | Req./min | Images/month |
|---|---|---|---|---|
| Free | $0 | Gemma 4 12B | 5 | 0 (paid from balance) |
| Starter | $39 | Gemma + Qwen3.6 35B + embeddings | 15 | 50 |
| Standard | $99 | All (includes Coder) | 40 | 300 |
| Pro | $249 | All + priority | 120 | 1,500 |
For volumes above Pro or specific needs, see Support.
Text: unlimited within your plan
Chat and embeddings calls are not billed per token. Control is by requests per minute (fair use) — each plan has its own limit. Use it freely within that limit.
Images: quota + overage
Each plan includes a monthly image quota. Above it, each image costs $0.03, debited from your prepaid balance.
The requests/min limit is the fair way to share the infrastructure. When you exceed it, the API responds with 429 — just lower your rate or apply backoff. See Errors & limits.