Cost optimization

How billing is shown

User-facing balance uses 积分 (points). Internal raw quota converts as:

raw_quota ÷ 500000 = USD
1 USD = 10 积分

Use the console for balance and usage. Account APIs (access token) expose profile/quota fields.

How to control cost and quality via model tiers & dynamic groups

OmniMux provides native stateless per-request group routing, allowing you to choose between cost optimization and production stability with a single API key:

1. Three invocation modes

Tier	Request Syntax	Typical Use Case	Billing & Routing
Default Auto Mode	Bare model name `"model": "seedance-2-5"`	Onboarding, drafts, batch creation	Default for new keys. Resolves lowest-cost channels first with automatic cross-group retry for SLA protection.
Global Standard Tier	Add `@standard` suffix `"model": "seedance-2-5@standard"` or `-H "X-Omnimux-Group: standard"`	Production pipelines, official SLA	Fixed 1.0 base multiplier, routed to official or premier enterprise lines.
Model-Specific Discounts	Add model-specific group `"model": "seedance-2-5@seedance-cheap"` `"model": "gemini-3.8-flash@gemini-cheap"`	Massive scaling, cost-sensitive jobs	Fixed custom discount (e.g. 75% off for Seedance Cheap, 70% off for Gemini Cheap), physically isolated channels.

2. Code examples

Method A: Model Suffix Syntax (Recommended for all clients/SDKs)

{
  "model": "seedance-2-5@seedance-cheap",
  "prompt": "A peaceful ocean wave at sunrise, 4k"
}

Method B: HTTP Header (Ideal for backend service integration)

curl -X POST "https://api.omnimux.ai/v1/chat/completions" \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -H "X-Omnimux-Group: gemini-cheap" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How to reduce cost

Pick the right model — cheaper/smaller models for simple jobs; enum lists capability, not equal price.
Cap generation — set sensible max_tokens / max_completion_tokens.
Bound multipliers — image n, video duration, resolution affect precharge/settlement; out-of-range values return 400.
Async video — create often precharges, then settles on completion/refund path. Use realistic duration/specs.
Cache — cache identical chat or social-data reads on the client.
Streaming — stream: true can improve UX; abort early only if your product allows and you understand billing still follows live settlement.
Watch 402 — insufficient balance fails pre-consume with 402 insufficient_quota.

Avoid

Load-testing expensive video/image models with production keys
Calling raw_quota “积分” in product UI
Guessing non-live model ids

Console

Balance, logs, and model access

​How billing is shown

​How to control cost and quality via model tiers & dynamic groups

​1. Three invocation modes

​2. Code examples

​Method A: Model Suffix Syntax (Recommended for all clients/SDKs)

​Method B: HTTP Header (Ideal for backend service integration)

​How to reduce cost

​Avoid