Pay-as-you-go
Fair & Transparent Pricing.
Scale without surprises.
Pay only for the tokens you process. No monthly subscriptions, no hidden commitments, and zero maintenance fees.
Google Models
| Model Name | Modality | Billing Unit | Price (Input / Output) |
|---|---|---|---|
Gemini 3 Flash Preview | LLM | Per 1M tokens | $0.50 in / $3.00 out |
Gemini 3 Pro Preview | LLM | Per 1M tokens | $2.00 in / $12.00 out |
Nano Banana Pro | Image/LLM | Per 1M tokens | $2.00 in / $12.00 out |
Gemini 2.5 Pro | LLM | Per 1M tokens | $1.25 in / $10.00 out |
Gemini 2.5 Flash | LLM | Per 1M tokens | $0.30 in / $2.50 out |
Nano Banana | Image/LLM | Per 1M tokens | $0.15 in / $0.60 out |
Anthropic Models
| Model Name | Modality | Billing Unit | Price (Input / Output) |
|---|---|---|---|
Claude Haiku 4.5 | LLM | Per 1M tokens | $1.00 in / $5.00 out |
Claude Sonnet 4.5 | LLM | Per 1M tokens | $3.00 in / $15.00 out |
Claude Opus 4.5 | LLM | Per 1M tokens | $5.00 in / $25.00 out |
OpenAI Models
| Model Name | Modality | Billing Unit | Price (Input / Output) |
|---|---|---|---|
GPT 5.2 | LLM | Per 1M tokens | $20.00 in / $60.00 out |
GPT-4o | LLM | Per 1M tokens | $5.00 in / $15.00 out |
Global Edge Network
Requests are routed to the nearest available data center for lowest latency and highest reliability.
Enterprise Security
SOC 2 Type II compliant infrastructure with end-to-end encryption for all API traffic.
Unified SDK
Switch between models instanty by changing just one parameter in your code.