Skip to main content
AI Gateway

One API for the models you actually use.

Compare live model pricing and availability, then call leading AI models through one OpenAI-compatible API.

Open dashboard
01 / Packages

Pick a model pack, keep the math simple.

Free tokens and paid model packs live here. Each paid pack is reserved for the exact model on its card.

Free snack

Enjoy a small token snack for the free models that are available today.

No free snack is open right now.

When the next one opens, its claim terms will appear here.

Model packs

Use a paid pack only with its named model. It never silently falls back to PAYG.

Paid model packs are coming soon.

A pack appears here only after its model and price are published for sale.

02 / Model catalog

All models, current pricing.

Prices are shown per one million input, output, or cache tokens. Model availability is refreshed every 30 seconds.

62 model11 familiesPAYGIDR / 1M token
Family / modelInput priceIDR + USD / 1MOutput priceIDR + USD / 1MCache priceInput / output · IDR / 1MAvailability
Claude Fable 5claude-fable-5ClaudeRp 70.850$3.9555Official $10.00Rp 354.250$19.7776Official $50.00Rp 7.085 inRp 35.425 outAvailable
Claude Fable 5.1claude-fable-5.1ClaudeRp 71.500$3.9918Official $10.00Rp 357.350$19.9506Official $50.00Rp 7.150 inRp 35.735 outAvailable
Claude Haiku 4.5claude-haiku-4.5ClaudeRp 7.150$0.3992Official $1.00Rp 35.750$1.9959Official $5.00Rp 715 inRp 3.575 outAvailable
Claude Opus 4.6claude-opus-4.6ClaudeRp 35.750$1.9959Official $5.00Rp 178.700$9.9767Official $25.00Rp 3.575 inRp 17.870 outAvailable
Claude Opus 4.6 Thinkingclaude-opus-4.6-thinkingClaudeRp 35.750$1.9959Official $5.00Rp 178.700$9.9767Official $25.00Rp 3.575 inRp 17.870 outAvailable
Claude Opus 4.7claude-opus-4.7ClaudeRp 35.750$1.9959Official $5.00Rp 178.700$9.9767Official $25.00Rp 3.575 inRp 17.870 outAvailable
Claude Opus 4.8claude-opus-4.8ClaudeRp 35.750$1.9959Official $5.00Rp 178.700$9.9767Official $25.00Rp 3.575 inRp 17.870 outAvailable
Claude Opus 5claude-opus-5ClaudeRp 35.750$1.9959Official $5.00Rp 178.700$9.9767Official $25.00Rp 3.575 inRp 17.870 outAvailable
Claude Sonnet 4.5claude-sonnet-4.5ClaudeRp 21.450$1.1975Official $3.00Rp 107.250$5.9877Official $15.00Rp 2.145 inRp 10.725 outAvailable
Claude Sonnet 4.6claude-sonnet-4.6ClaudeRp 21.450$1.1975Official $3.00Rp 107.250$5.9877Official $15.00Rp 2.145 inRp 10.725 outAvailable
Showing 1-10 of 62
1 / 7
03 / How costs work

Pay only for the tokens your request processes.

Every model has separate live rates for input, output, and cache tokens. The model price is confirmed before the request runs.

Input tokens
Text, instructions, and context you send to the model.
Output tokens
Text generated by the model in its response.
Cache tokens
Eligible repeated context served from the isolated response cache.
04 / Cost calculator

Estimate a request from the current catalog price.

Enter a realistic token count. This estimate reads the same public price data as the model catalog above.

05 / Get started

Create an account, add credit, make a key, then call the API.

  1. 01Create an accountRegister, verify your email, then sign in to open the dashboard.
  2. 02Add creditYour balance is ready to use after payment is confirmed.
  3. 03Create an API keyUse one key for every active model and set limits that suit your work.
  4. 04Choose a modelCheck the live catalog, then select the model ID for your request.
  5. 05Send a requestUse the OpenAI-compatible chat endpoint. Streaming is available when you need it.
06 / Controls and trust

Set limits before a key starts spending.

Budget by key
Set a daily or monthly budget for each API key.
Output and traffic limits
Set a maximum output, requests per minute, and concurrent requests.
Key management
Create, edit, or remove API keys from the dashboard.
Usage records
Review tokens, status, and charge without showing prompt or completion text in usage history.
07 / FAQ

Questions about the API Gateway

How do I pay?

Add credit through EidosStack checkout. Your balance becomes available after payment is confirmed.

How do token packages work?

For a paid model with an active package, the package quota is used first. If there is no active package for that model, the request uses your PAYG wallet. An exhausted active package returns an insufficient-package-quota error and does not silently charge PAYG.

How are prompts and responses handled?

Prompt text and completion text are not shown in usage history or placed in cache keys. Eligible requests can use a short-lived response cache that is isolated to the same account.

What models are available?

The live catalog shows the models that are currently available, their token prices, and their cache prices. It refreshes availability every 30 seconds.

08 / GUIDE