Buy tokens, not seats
Every plan unlocks all 33 models with streaming, tool calling, and vision. The only difference is how many tokens you get each month.
Free
Try every model with no card required.
Forever — no card required
- 5M tokens / month
- 60 requests / min
- All chat models
- Streaming, tools & vision
- Community support
Starter
For side projects and prototypes.
$35 billed yearly
$0.07 per 1M tokens
- 50M tokens / month
- 120 requests / min
- All models
- Streaming, tools & vision
- Email support
Basic
For apps with steady daily traffic.
$57.50 billed yearly
$0.0575 per 1M tokens
- 100M tokens / month
- 300 requests / min
- All models
- Usage analytics
- Email support
Pro
For production workloads and small teams.
$95 billed yearly
$0.0475 per 1M tokens
- 200M tokens / month
- 600 requests / min
- All models
- Usage analytics
- Priority support
Scale
For high-volume, multi-service workloads.
$155 billed yearly
$0.031 per 1M tokens
- 500M tokens / month
- 1,200 requests / min
- All models + early access
- Usage analytics
- Priority support
Unlimited
No monthly token cap. Rate limits still apply.
$500 billed yearly
- Unlimited tokens
- 3,000 requests / min
- All models + early access
- Usage analytics
- Dedicated support
- Custom rate limits on request
Run out mid-month? Nothing breaks.
Once your allowance is used, requests bill against your account balance at each model's per-token rate —
see the model catalog for exact prices.
With an empty balance you get a clear 402 instead of a surprise invoice.
Compare plans
| Plan | Price / mo | Tokens / mo | Per 1M | Requests / min | Tokens / min |
|---|---|---|---|---|---|
| Free | Free | 5M | — | 60 | 100,000 |
| Starter | $3.50 | 50M | $0.07 | 120 | 200,000 |
| Basic | $5.75 | 100M | $0.0575 | 300 | 500,000 |
| Pro Best value | $9.50 | 200M | $0.0475 | 600 | 1,000,000 |
| Scale | $15.50 | 500M | $0.031 | 1,200 | 2,000,000 |
| Unlimited | $50 | Unlimited | — | 3,000 | 5,000,000 |
Tokens count prompt + completion combined. Rate limits are enforced per minute and reported in
X-RateLimit-* response headers.
Pricing questions
Each plan includes a monthly token allowance. Tokens cover both your prompt and the model's reply, and the allowance resets every month. Requests draw from the allowance first, so you are not billed per call until it runs out.
Requests fall back to your account balance and are billed per token at each model's published rate. If the balance is empty, requests return HTTP 402 with a clear error instead of failing silently — top up or upgrade and you resume immediately.
There is no monthly token cap on the Unlimited plan. Per-minute rate limits still apply (3,000 requests and 5M tokens per minute) to keep the service stable for everyone. If you need more, contact us for custom limits.
Yes, any time. Upgrades take effect immediately and your allowance is refreshed. Downgrades apply from the next billing period, so you keep what you have already paid for.
Every plan, including Free, has access to all 33 models with streaming, tool calling, vision, and reasoning. Plans differ only in token allowance and rate limits — never in model access.
Paddle (Credit/Debit cards, Apple Pay, Google Pay, iDEAL), Binance Pay, and cryptocurrency (USDT/BTC). Payments are verified automatically and activate your plan immediately.
Yes — a 7-day money-back guarantee on all paid plans. See our Refund Policy or contact support and we will process it.
Still not sure which plan fits?
Start free — upgrade any time