Pricing

Pay for tokens, not seats.

No monthly plans. No seats. Use account credits, call any model, and pay the exact per-token rate. Self-serve recharge is coming soon.

Get API key See every model

How credits work

Three steps. No subscriptions, no auto-renew, no surprise invoices.

Step 1

Start with credits

Early access accounts use operator-issued prepaid balance. Self-serve recharge will replace this flow later.

Step 2

Call any model

One sk-maas-... key works across Claude, Gemini, OpenAI, MiniMax. We pass the request through and meter the cost.

Step 3

See exact cost

Every request shows up in Activity with tokens, latency, and dollars. Run out? Requests 402, never overcharged.

Recharge status:Self-service payments are not enabled yet.Operator-issued credits still spend against the same rates below.

Sample rates

Pass-through provider prices with a thin managed-platform margin.

All models

Model	Provider routes	Status	Input / MTok	Output / MTok
Gemini 3.1 Flash-Lite `gemini-3.1-flash-lite`	Google AI Studio	Available	$0.25	$1.50
Gemini 3.5 Flash `gemini-3.5-flash`	Google AI Studio	Available	$1.50	$9.00
Nano Banana Pro `nano-banana-pro`	Google AI Studio	Available	-	$0.134 per image

One catalog for every model route.

Browse 89 canonical models across 13 providers, then choose the route that matches your cost, latency, and availability needs.

Unified model catalog

Claude, Gemini, OpenAI, MiniMax, GLM, Qwen, and more behind one OpenAI-compatible API.

89 canonical models grouped from provider routes
Text, image, video, audio, embeddings, and rerank routes
Model detail pages with SDK-ready examples

Provider routes

Use the same model through native, Bedrock, Vertex, SandBase, or other configured routes.

27 routes currently backed by active upstream credentials

Self-hosted or dedicated capacity?

For teams that need SSO, on-prem deployment, custom provider adapters, or reserved upstream capacity — talk to us. Custom contract, not a SKU.

Contact sales

Questions, briefly answered.

Are there monthly plans or seats?+

No. Every account is pay-as-you-go. During early access, credits are operator-issued; later, self-service recharge will add balance on demand. Nothing recurs.

How is each call priced?+

Text is per-token in + per-token out. Image is per-image. Video is per-second. We use the upstream provider's published rates with a small managed-platform margin baked in — every request shows its exact cost in Activity.

What happens when credits run out?+

Requests fail with HTTP 402 when balance is below the required request hold. Add balance to continue routing calls.

Can I bring my own provider key?+

Not on the managed plan. Miavo runs the upstream credentials so a single sk-maas-… key gets you Claude + Gemini + OpenAI + MiniMax. For full upstream control, the self-host build is the path.

OpenAI compatibility?+

Drop-in. The /v1/chat/completions endpoint speaks the OpenAI schema across all providers — streaming, tool calls, image inputs translated automatically.

Refunds on unused credits?