Pay as you go
Starter
$0 / month
No subscription. Top up in USD and pay per request.
- 180+ models on one endpoint
- Per-request itemized billing
- Automatic failover and health-aware routing
- Usage export (CSV)
- Email support
Pricing
Pay for what you use. Nothing else.
No seats, no hidden fees. Prepay a USD balance, top up in your currency, and read every request on your invoice. Plans below are illustrative demo values.
Plans
Demo data Demo data: every figure on this page is illustrative and is not a live quote.
Most popular Popular
Pro
$20 / month
For individuals shipping production traffic every day.
- $20 included credit each month
- 5% lower model rates
- Priority routing during peak load
- Higher rate limits per key
- Email support with 1 business day target
Teams
Team
$99 / month
Shared billing, invoices and a data processing agreement.
- $100 included credit each month
- Up to 5 members with per-member quotas
- 10% lower model rates
- Invoices, VAT ID and DPA
- Priority support channel
Estimate
Cost calculator
Estimate a single request from its token counts. All maths runs in your browser; nothing is sent anywhere.
Demo rates · billed in USD · local currency and taxes are shown at checkout.
Model prices
Per-model rates
USD per 1M tokens. Cached input is billed only where the model supports it.
| Model | Vendor | Input / 1M | Output / 1M | Cached / 1M | Context |
|---|---|---|---|---|---|
| claude-opus-5.5 | Anthropic | $15.00 | $75.00 | $1.50 | 200K |
| claude-sonnet-4.5 | Anthropic | $3.00 | $15.00 | $0.30 | 200K |
| claude-haiku-4.5 | Anthropic | $0.80 | $4.00 | $0.08 | 200K |
| gpt-6-astra | OpenAI | $5.00 | $20.00 | $0.50 | 400K |
| gpt-6-mini | OpenAI | $0.60 | $2.40 | $0.06 | 400K |
| gpt-5.5-codex | OpenAI | $1.50 | $9.00 | $0.15 | 400K |
| gemini-3.5-pro | $2.50 | $10.00 | $0.25 | 1M | |
| gemini-3.5-flash | $0.30 | $1.20 | $0.03 | 1M | |
| gemini-3-ultra | $4.00 | $16.00 | $0.40 | 1M | |
| grok-5 | xAI | $3.00 | $15.00 | — | 256K |
| deepseek-v4.1 | DeepSeek | $0.28 | $0.42 | $0.03 | 128K |
| deepseek-r2 | DeepSeek | $0.55 | $2.19 | $0.14 | 160K |
| qwen-4-max | Qwen | $1.20 | $6.00 | $0.12 | 256K |
| kimi-k3 | Moonshot | $0.90 | $3.60 | $0.09 | 256K |
| mistral-large-3 | Mistral | $1.80 | $5.40 | — | 128K |
| llama-5-405b | Meta | $2.20 | $6.60 | — | 128K |
| qwen-4-vl | Qwen | $0.70 | $2.80 | $0.07 | 128K |
| whisper-3 | OpenAI | $0.36 | $0.00 | — | audio |
No matching models. Try a different name or vendor.
Billing FAQ
Billing questions
How is usage billed?
Every request is itemized by input, output, cached and reasoning tokens. You are billed in USD against your prepaid balance; subscriptions add included credit.
Do failed requests cost anything?
No. Requests that fail before the upstream returns a token are not charged. Partial streams are billed for delivered tokens only.
Is prompt caching cheaper?
Yes, where the model supports it. Cached input tokens are billed at the cached rate shown in the table above.
How do refunds work?
Unused prepaid balance is refundable within 14 days of purchase under the refund policy. See /legal/refund. Subscription fees are prorated only where required by law.
Ready to ignite? Start with $1.
Start with $1.
Get 180+ models.
Create account
No card required to start Cancel anytime GDPR ready