FAQ
Plain-language answers for people who have never used an AI API, plus links for developers who want the deeper detail. New to all of this? Start at getting started or the glossary.
Using OMA with your tools
Which clients can connect to OMA?
Clients that let you configure a Chat Completions base URL, key and model can use
https://www.oma-ai.com/api/v1. The Messages adapter supports text and function tools. Check /docs#integrations against the features your client requires; client-specific setup and full feature compatibility are not verified.How do I migrate an app that already uses OpenAI?
Set the Chat Completions base URL to
https://www.oma-ai.com/api/v1, use an OMA API key and choose an available OMA model ID. Compare your request fields with /docs#endpoints. The Responses API is unsupported, and undocumented Chat Completions fields are ignored.Does OMA support the Anthropic Messages API?
OMA exposes a Messages adapter for text and function tools. Image and document blocks are rejected. Extended-thinking and prompt-cache fields are ignored and not forwarded. See /docs#endpoints for the supported request and response shapes.
Reliability & safety
How does OMA handle provider outages?
A circuit breaker keeps traffic off an unhealthy upstream route. If the requested model has a configured fallback, OMA can retry that mapped model on the fallback route; otherwise the request returns an upstream
/unavailable error rather than silently swapping to a different model. Check /status for live gateway health.Can a provider see my prompts?
The OMA gateway does not persist prompt or completion content and meters billing metadata. Website chat saves conversations and drafts in your browser. However, the inference provider that serves a request must process that content to answer it, so provider-side retention guarantees depend on the model and provider you select. See /privacy for the exact data-flow.
What are the rate limits?
There are no per-plan rate tiers; a single shared token-bucket set applies, with per-model overrides where a provider needs them (for example llama-3.3-70b). The docs list the burst, refill, sustained RPM, and per-model token ceilings at /docs#rate-limits. Rate-limit headers are returned on each response.
Getting started
What is OMA?
OMA (Open Model Access) provides browser chat and an API gateway for a curated model catalog. One account holds your API keys, prepaid credits and usage records. The API supports Chat Completions and a documented Messages subset.
Do I need to know how to code?
No. You can try AI immediately in the free chat playground at /chat — no account needed. Guests can use available OMA-AI website-chat models with a daily message cap. MiniMax M2.7 is the default; check the model catalog for current availability. You only need the API (and an API key) when you want to build something, like an app or a script.
How do I start using it?
Three steps: (1) try free website chat on an available eligible model — no account needed; (2) sign in with your email (magic link) or crypto wallet and create an API key; (3) add a little credit and call the API. The full walkthrough is on the /getting-started page.
What can I do with it?
Chat, write code, and summarize documents. Some models accept image inputs. Pick a model from the catalog and call it through one OpenAI-compatible API.
Is there a free tier?
Yes. Website chat has a daily free allowance on eligible OMA-AI models, subject to availability, with more messages once you sign in. API-key calls always spend credits, even on those models; the free tier lives in browser chat. See /pricing for limits.
Accounts, keys & privacy
What is an API key?
An API key is like a password that lets your code (or an AI tool you use) talk to OMA on your behalf. It looks like `oma_sk_...`. Keep it secret — anyone with your key can spend your credits. You can create and revoke keys from the dashboard.
Do you store my API keys?
The server database stores a SHA-256 hash and key metadata. The raw key is shown at creation; browser chat can also hold an installed key in an HttpOnly cookie for up to seven days. Revoke lost keys from the dashboard. See /privacy for stored data and retention details.
What is a magic link?
A magic link is a sign-in without a password. You enter your email, we send you a link, you click it, and you're signed in. No passwords to remember.
What is a wallet (SIWE) and do I need one?
SIWE (Sign-In With Ethereum) lets you sign in with a crypto wallet instead of an email. You do NOT need a wallet for email sign-in or card checkout when it is enabled. A wallet is needed for direct USDC deposits and the advanced x402 settlement flow.
Is my data private?
The OMA gateway does not persist prompt or completion content. Website chat history stays in your browser and does not sync between devices. The inference provider that serves a request must process that content, and provider retention/privacy guarantees depend on the selected provider and model. See /privacy for the data-flow details.
Money & payments
How do I pay?
Deposit USDC on Base, then spend credits per request. Agents can also fund via x402 verify
/settle, which credits the same balance before API spend. Card checkout through Polar is available only when it is enabled, and the credits page shows its live status. Credits never expire while your account is active.What is USDC? What is Base?
USDC is a U.S.-dollar-denominated stablecoin issued by Circle. It aims to track $1, though its market price can vary. Base is the blockchain network where OMA accepts USDC payments. See /glossary for more detail.
What is x402?
x402 is a crypto payment flow for agents: sign a USDC authorization on Base, verify at
/x402/verify, settle to credit your account, then call the API with your key. Inference itself is billed from that credit balance — not attached as a mid-request 402 on chat today.How much does it cost?
API cost depends on the selected model and the number of input and output tokens. Rates are quoted per million tokens, with no subscription or monthly fee. Website chat has a separate daily free allowance on eligible models. See /pricing for current rates and limits.
What happens when I run out of credits?
Paid requests return HTTP 402 when spendable credits cannot cover the required reservation. Pending requests or refund adjustments can reduce available credits. Check your balance and holds in the dashboard before topping up. Your account and keys remain available.
Models, tokens & chat
What is a model?
A model is a specific AI system with different strengths, context limits, and prices. You pick the model id per request; OMA routes that requested model to its configured upstream provider.
What is a token?
A token is a unit used by the selected model to process input and output. Token counts vary by model and content. OMA quotes API prices per million tokens and records usage returned by the provider.
What is a context window?
The context budget covers the request input and requested output. Each model page lists the configured context and output ceilings with verification sources. Unpublished provider limits are marked unverified; tokenization can differ between the gateway estimate and provider.
What does 'OpenAI-compatible' mean?
OMA supports the Chat Completions fields and response shapes listed in /docs. A client needs a configurable base URL, an OMA key and a catalog model ID. The Responses API is unsupported; check required features before migrating a client.
What is streaming?
Streaming returns response chunks as they are generated. Clients can display partial output while continuing to read the stream. Handle in-stream errors and retain the request ID if generation is interrupted.
Which model should I pick?
Start with a budget or mid model for everyday chat, and reach for frontier models for hard math, code, or long documents. The chat UI shows each model's price, context length, and strengths, and /models has the full catalog.
Do you support multimodal inputs?
Some catalog models accept image inputs alongside text. Check the model page or capability filters before relying on vision support. Compatible models use the OpenAI multimodal `messages[].content` array shape (for example text and image_url parts).
For developers
Where are the API docs?
The full reference is at /docs — quickstart, authentication, every endpoint, streaming, rate limits, errors, and the x402 flow. There's a search box at the top.
Is there a quickstart?
Yes. /getting-started covers website chat, account setup, prepaid credits and a first API request. /docs#quickstart provides the API reference version.
Can my AI agent use OMA?
Yes. /agent-skill.md explains how to sign in, create an API key, discover available models, and make a request. It also documents optional x402 funding, which requires the payer's wallet session and moves real funds. OMA publishes an agent card at /.well-known/agent-card.json and a machine-readable index at /llms.txt.
What happens when a model provider is down?
The circuit breaker stops repeatedly sending traffic to an unhealthy route. If the requested model has a configured fallback, OMA can retry that mapped model there. If no fallback is configured, the request can return an upstream
/unavailable error rather than silently substituting a different model.I got a 402 error — what now?
A 402 means payment is required — usually your credit balance is empty. Top up at /deposit (USDC or card when enabled), or use the x402 verify
/settle flow to credit your balance, then retry with an API key (docs: /docs#x402).How do I troubleshoot x402 errors?
Check the Base network, USDC balance, current treasury recipient, signature fields, validity window, and a fresh nonce. EIP-3009 uses a signed transfer authorization; a separate token approval is not required. Settlement needs a SIWE session for the same wallet that paid. If a transaction hash was returned, check it before authorizing another transfer. See /docs#x402 for the full flow.