Pricing

Usage-based pricing on the models you route.

Serica display rates on the live stack. Self-serve through the app, or talk to us for committed volume.

Indicative rates

The Serica model subset and display pricing layer. Same API path as Token360, scoped for creative-industry routing.

Video generation

Veo 3.1

Google

$0.44/s
Seedance 2.0

ByteDance

$0.18/s
Kling V3

Kuaishou

$0.22/s

Image generation

Nano Banana Pro

Google

$0.06/image
Seedream 4.5

ByteDance

$0.04/image
GLM-Image

Zhipu

$0.035/image

Language and vision

GPT-5.2

OpenAI

$4.50 / 1M tokens
Claude Opus 4.7

Anthropic

$5.20 / 1M tokens
DeepSeek V4

DeepSeek

$2.20 / 1M tokens

Indicative Serica display rates on the live Token360 stack. Volume commitments and routing mix may adjust your final rate card.

Priced to your volume

Committed-use rates that fall as you scale. Direct supply means competitive, source-level pricing, metered to what you route.

Pay for what you route

One invoice across every model, video, image, and language. No per-model contracts — top up your wallet and start.

Self-serve or sales-led

Create an account, add credits, and call the API today. For enterprise volume, our team will shape a custom rate card.

Ready to route your first request?

Create an account, top up your wallet, and point your SDK at the Serica API endpoint.